hanzoai/hanzo.ai
2
0
Fork 0
mirror of https://github.com/hanzo-apps/hanzo.ai.git synced 2026-10-28 07:32:52 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
main
hanzo.ai/lib/data/served.json
T
zeekay b082379a0f counts: one definition of how many repositories we have, read from GitHub today 
The landing said 686 public repositories (non-fork, not archived) while other
pages said 800+ (every public repository, forks included): two numbers for one
thing, and 125 of the 825 were other people's code. Both now count the public
repositories we wrote, forks left out and archived kept: 725 across the twelve
organizations, so pages say 700+. The activity block reads that same set, so its
commit total gains the archived repositories' history: 84,505 commits in the
year, 380 this week, 166 repositories with a commit this month. Models are
557, as /v1/models answers today.
2026-10-27 01:35:13 -07:00

5772 lines
214 KiB
JSON
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"served": [
{
"id": "aion-labs/aion-2.0",
"name": "Aion-2.0",
"description": "Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....",
"owned_by": "aion-labs",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "aion-labs/aion-3.0",
"name": "Aion-3.0",
"description": "Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...",
"owned_by": "aion-labs",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "aion-labs/aion-3.0-mini",
"name": "Aion-3.0-Mini",
"description": "Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...",
"owned_by": "aion-labs",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "aion-labs/aion-3.5",
"name": "Aion 3.5",
"description": "Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...",
"owned_by": "aion-labs",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "aion-labs/aion-3.5-mini",
"name": "Aion 3.5 Mini",
"description": "Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...",
"owned_by": "aion-labs",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "aion-labs/aion-rp-llama-3.1-8b",
"name": "Aion-RP 1.0 (8B)",
"description": "Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...",
"owned_by": "aion-labs",
"context_window": 32768,
"outputs": [
"text"
]
},
{
"id": "alibaba/happyhorse-1.0",
"name": "HappyHorse 1.0",
"description": "HappyHorse 1.0 is a video generation model from Alibaba. It generates short videos from a text prompt, a single starting image, or a set of reference images, with output up...",
"owned_by": "alibaba",
"outputs": [
"video"
]
},
{
"id": "alibaba/happyhorse-1.1",
"name": "HappyHorse 1.1",
"description": "HappyHorse 1.1 is a video generation model from Alibaba. It generates short videos from a text prompt, a single starting image, or a set of reference images, with output up...",
"owned_by": "alibaba",
"outputs": [
"video"
]
},
{
"id": "alibaba/wan-2.6",
"name": "Wan 2.6",
"description": "Alibaba's most advanced video generation model, supporting over 10 visual creation capabilities in a unified system. Wan 2.6 generates 1080p video at 24fps from text, images, reference videos, or audio,...",
"owned_by": "alibaba",
"outputs": [
"video"
]
},
{
"id": "alibaba/wan-2.7",
"name": "Wan 2.7",
"description": "Wan 2.7 is a video generation model from Alibaba. It supports text-to-video, image-to-video with first and last frame control, and reference-to-video, where multiple reference images guide the style and content...",
"owned_by": "alibaba",
"outputs": [
"video"
]
},
{
"id": "alibaba/wan-3.0",
"name": "Wan 3.0",
"description": "Wan 3.0 is a video generation model from Alibaba for text-to-video, image-to-video, and reference-guided video generation. It produces 480p, 720p, or 1080p video with durations from 2 to 30 seconds.",
"owned_by": "alibaba",
"outputs": [
"video"
]
},
{
"id": "alibaba/wan-3.0-prime",
"name": "Wan 3.0 Prime",
"description": "Wan 3.0 Prime is a fast-mode variant of [Wan 3.0](https://openrouter.ai/alibaba/wan-3.0) from Alibaba. It supports text-to-video and first-frame image-to-video generation.",
"owned_by": "alibaba",
"outputs": [
"video"
]
},
{
"id": "amazon/nova-2-lite-v1",
"name": "Nova 2 Lite",
"description": "Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...",
"owned_by": "amazon",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "amazon/nova-lite-v1",
"name": "Nova Lite 1.0",
"description": "Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...",
"owned_by": "amazon",
"context_window": 300000,
"outputs": [
"text"
]
},
{
"id": "amazon/nova-micro-v1",
"name": "Nova Micro 1.0",
"description": "Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...",
"owned_by": "amazon",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "amazon/nova-premier-v1",
"name": "Nova Premier 1.0",
"description": "Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.",
"owned_by": "amazon",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "amazon/nova-pro-v1",
"name": "Nova Pro 1.0",
"description": "Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...",
"owned_by": "amazon",
"context_window": 300000,
"outputs": [
"text"
]
},
{
"id": "anthracite-org/magnum-v4-72b",
"name": "Magnum v4 72B",
"description": "This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).\n\nThe model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).",
"owned_by": "anthracite-org",
"context_window": 32768,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-fable-5",
"name": "Claude Fable 5",
"description": "Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-fable-5.1",
"name": "Claude Fable 5.1",
"description": "Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-fable-5.1:batch",
"name": "Claude Fable 5.1 (batch)",
"description": "Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-fable-5:batch",
"name": "Claude Fable 5 (batch)",
"description": "Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-haiku-4.5",
"name": "Claude Haiku 4.5",
"description": "Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...",
"owned_by": "anthropic",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-haiku-4.5:batch",
"name": "Claude Haiku 4.5 (batch)",
"description": "Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...",
"owned_by": "anthropic",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-haiku-5.5",
"name": "Claude Haiku 5.5",
"description": "Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-haiku-5.5:batch",
"name": "Claude Haiku 5.5 (batch)",
"description": "Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-opus-4.1",
"name": "Claude Opus 4.1",
"description": "Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...",
"owned_by": "anthropic",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-opus-4.1:batch",
"name": "Claude Opus 4.1 (batch)",
"description": "Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...",
"owned_by": "anthropic",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-opus-4.5",
"name": "Claude Opus 4.5",
"description": "Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...",
"owned_by": "anthropic",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-opus-4.5:batch",
"name": "Claude Opus 4.5 (batch)",
"description": "Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...",
"owned_by": "anthropic",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-opus-4.6",
"name": "Claude Opus 4.6",
"description": "Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-opus-4.6:batch",
"name": "Claude Opus 4.6 (batch)",
"description": "Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-opus-4.7",
"name": "Claude Opus 4.7",
"description": "Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-opus-4.7:batch",
"name": "Claude Opus 4.7 (batch)",
"description": "Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-opus-4.8",
"name": "Claude Opus 4.8",
"description": "Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-opus-4.8:batch",
"name": "Claude Opus 4.8 (batch)",
"description": "Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-opus-5",
"name": "Claude Opus 5",
"description": "Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-opus-5.5",
"name": "Claude Opus 5.5",
"description": "Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-opus-5.5:batch",
"name": "Claude Opus 5.5 (batch)",
"description": "Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-opus-5:batch",
"name": "Claude Opus 5 (batch)",
"description": "Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-sonnet-4.5",
"name": "Claude Sonnet 4.5",
"description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-sonnet-4.5:batch",
"name": "Claude Sonnet 4.5 (batch)",
"description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-sonnet-4.6",
"name": "Claude Sonnet 4.6",
"description": "Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-sonnet-4.6:batch",
"name": "Claude Sonnet 4.6 (batch)",
"description": "Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-sonnet-5",
"name": "Claude Sonnet 5",
"description": "Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-sonnet-5.5",
"name": "Claude Sonnet 5.5",
"description": "Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-sonnet-5.5:batch",
"name": "Claude Sonnet 5.5 (batch)",
"description": "Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "anthropic/claude-sonnet-5:batch",
"name": "Claude Sonnet 5 (batch)",
"description": "Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...",
"owned_by": "anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "black-forest-labs/flux-3-video",
"name": "FLUX 3 Video",
"description": "FLUX.3 Video is a video generation model from Black Forest Labs. It supports text-to-video, image-guided generation with opening and closing keyframes, and video continuation workflows, making it suited for controlled...",
"owned_by": "black-forest-labs",
"outputs": [
"video"
]
},
{
"id": "bytedance-seed/seed-1.6",
"name": "Seed 1.6",
"description": "Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.",
"owned_by": "bytedance-seed",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "bytedance-seed/seed-1.6-flash",
"name": "Seed 1.6 Flash",
"description": "Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...",
"owned_by": "bytedance-seed",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "bytedance-seed/seed-2-1-turbo",
"name": "Seed 2.1 Turbo",
"description": "Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...",
"owned_by": "bytedance-seed",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "bytedance-seed/seed-2.0-code",
"name": "Seed-2.0-Code",
"description": "Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude...",
"owned_by": "bytedance-seed",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "bytedance-seed/seed-2.0-lite",
"name": "Seed-2.0-Lite",
"description": "Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...",
"owned_by": "bytedance-seed",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "bytedance-seed/seed-2.0-mini",
"name": "Seed-2.0-Mini",
"description": "Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...",
"owned_by": "bytedance-seed",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "bytedance-seed/seed-audio-1-0",
"name": "Seed Audio 1.0",
"description": "Seed Audio 1.0 is ByteDance Seed's non-streaming audio generation model. It produces speech and other audio from a natural-language text prompt that can describe the desired voice, tone, and sound...",
"owned_by": "bytedance-seed",
"outputs": [
"speech"
]
},
{
"id": "bytedance/seedance-1-5-pro",
"name": "Seedance 1.5 Pro",
"description": "ByteDance's next-generation audio-visual generation model with a 4.5B parameter Dual-Branch Diffusion Transformer architecture. Seedance 1.5 Pro generates video and audio simultaneously in a single unified pass — eliminating the timing...",
"owned_by": "bytedance",
"outputs": [
"video"
]
},
{
"id": "bytedance/seedance-2.0",
"name": "Seedance 2.0",
"description": "Seedance 2.0 is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It is particularly strong at preserving character consistency,...",
"owned_by": "bytedance",
"outputs": [
"video"
]
},
{
"id": "bytedance/seedance-2.0-fast",
"name": "Seedance 2.0 Fast",
"description": "Seedance 2.0 Fast is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It prioritizes generation speed and lower cost...",
"owned_by": "bytedance",
"outputs": [
"video"
]
},
{
"id": "bytedance/seedance-2.0-mini",
"name": "Seedance 2.0 Mini",
"description": "Seedance 2.0 Mini is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video with image, video, and audio inputs. It...",
"owned_by": "bytedance",
"outputs": [
"video"
]
},
{
"id": "bytedance/seedance-2.5",
"name": "Seedance 2.5",
"description": "Seedance 2.5 is a video generation model from ByteDance. It is suited for long-form storytelling, multimodal reference-based generation, video editing, and video extension. It supports first-frame and first-and-last-frame control, up...",
"owned_by": "bytedance",
"outputs": [
"video"
]
},
{
"id": "bytedance/ui-tars-1.5-7b",
"name": "UI-TARS 7B",
"description": "UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...",
"owned_by": "bytedance",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "canopylabs/orpheus-3b-0.1-ft",
"name": "Orpheus 3B",
"description": "Orpheus 3B is an English text-to-speech model from Canopy Labs, fine-tuned for natural prosody and expressive delivery. It offers 7 preset voices and is suited for narration, voice assistants, and...",
"owned_by": "canopylabs",
"outputs": [
"speech"
]
},
{
"id": "cognitivecomputations/dolphin-mistral-24b-venice-edition",
"name": "Uncensored",
"description": "Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...",
"owned_by": "cognitivecomputations",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "cohere/command-a",
"name": "Command A",
"description": "Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...",
"owned_by": "cohere",
"context_window": 256000,
"outputs": [
"text"
]
},
{
"id": "cohere/command-a-plus",
"name": "Command A+",
"description": "Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...",
"owned_by": "cohere",
"context_window": 192000,
"outputs": [
"text"
]
},
{
"id": "cohere/command-r-08-2024",
"name": "Command R (08-2024)",
"description": "command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...",
"owned_by": "cohere",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "cohere/command-r-plus-08-2024",
"name": "Command R+ (08-2024)",
"description": "command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...",
"owned_by": "cohere",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "cohere/command-r7b-12-2024",
"name": "Command R7B (12-2024)",
"description": "Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...",
"owned_by": "cohere",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "cohere/north-mini-code:free",
"name": "North Mini Code (free)",
"description": "North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...",
"owned_by": "cohere",
"context_window": 256000,
"outputs": [
"text"
]
},
{
"id": "deepgram/aura-2",
"name": "Aura-2",
"description": "Aura-2 is a multilingual text-to-speech model from Deepgram. It supports Deepgram’s canonical Aura-2 voice catalog for speech synthesis across multiple languages.",
"owned_by": "deepgram",
"outputs": [
"speech"
]
},
{
"id": "deepgram/flux-tts",
"name": "Flux TTS",
"description": "Flux TTS is a text-to-speech model from Deepgram. It is suited for natural, expressive English speech synthesis across Deepgram's Flux voice catalog.",
"owned_by": "deepgram",
"outputs": [
"speech"
]
},
{
"id": "deepseek/deepseek-chat",
"name": "DeepSeek V3",
"description": "DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...",
"owned_by": "deepseek",
"context_window": 163840,
"outputs": [
"text"
]
},
{
"id": "deepseek/deepseek-chat-v3-0324",
"name": "DeepSeek V3 0324",
"description": "DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...",
"owned_by": "deepseek",
"context_window": 163840,
"outputs": [
"text"
]
},
{
"id": "deepseek/deepseek-chat-v3.1",
"name": "DeepSeek V3.1",
"description": "DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...",
"owned_by": "deepseek",
"context_window": 163840,
"outputs": [
"text"
]
},
{
"id": "deepseek/deepseek-r1-0528",
"name": "R1 0528",
"description": "May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...",
"owned_by": "deepseek",
"context_window": 163840,
"outputs": [
"text"
]
},
{
"id": "deepseek/deepseek-v3.1-terminus",
"name": "DeepSeek V3.1 Terminus",
"description": "DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...",
"owned_by": "deepseek",
"context_window": 163840,
"outputs": [
"text"
]
},
{
"id": "deepseek/deepseek-v3.2",
"name": "DeepSeek V3.2",
"description": "DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...",
"owned_by": "deepseek",
"context_window": 163840,
"outputs": [
"text"
]
},
{
"id": "deepseek/deepseek-v3.2-exp",
"name": "DeepSeek V3.2 Exp",
"description": "DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...",
"owned_by": "deepseek",
"context_window": 163840,
"outputs": [
"text"
]
},
{
"id": "deepseek/deepseek-v4-flash",
"name": "DeepSeek V4 Flash 0423",
"description": "DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...",
"owned_by": "deepseek",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "deepseek/deepseek-v4-flash-0731",
"name": "DeepSeek V4 Flash 0731",
"description": "DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....",
"owned_by": "deepseek",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "deepseek/deepseek-v4-flash-vision-exp",
"name": "DeepSeek V4 Flash Vision Exp",
"description": "DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...",
"owned_by": "deepseek",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "deepseek/deepseek-v4-pro",
"name": "DeepSeek V4 Pro 0423",
"description": "DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...",
"owned_by": "deepseek",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "deepseek/deepseek-v4-pro-0813",
"name": "DeepSeek V4 Pro 0813",
"description": "DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.",
"owned_by": "deepseek",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "deepseek/deepseek-v4.1-flash",
"name": "DeepSeek V4.1 Flash",
"description": "DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...",
"owned_by": "deepseek",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "deepseek/deepseek-v4.1-flash-1017",
"name": "DeepSeek V4.1 Flash 1017",
"description": "DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...",
"owned_by": "deepseek",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "deepseek/deepseek-v4.1-flash:batch",
"name": "DeepSeek V4.1 Flash (batch)",
"description": "DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...",
"owned_by": "deepseek",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "dots-studio/dots-3-note-preview:free",
"name": "Dots3-Note Preview (free)",
"description": "Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...",
"owned_by": "dots-studio",
"context_window": 512000,
"outputs": [
"text"
]
},
{
"id": "elevenlabs/eleven-flash-v2",
"name": "Eleven Flash v2",
"description": "Eleven Flash v2 is an English-only, ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time English use cases, and has a 30,000-character request limit.",
"owned_by": "elevenlabs",
"outputs": [
"speech"
]
},
{
"id": "elevenlabs/eleven-flash-v2.5",
"name": "Eleven Flash v2.5",
"description": "Eleven Flash v2.5 is an ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time use cases, supports 32 languages, and has a 40,000-character request limit.",
"owned_by": "elevenlabs",
"outputs": [
"speech"
]
},
{
"id": "elevenlabs/eleven-multilingual-v2",
"name": "Eleven Multilingual v2",
"description": "Eleven Multilingual v2 is a text-to-speech model from ElevenLabs. It is suited for lifelike, consistent long-form narration such as voice-overs and audiobooks, supports 29 languages, and has a 10,000-character request...",
"owned_by": "elevenlabs",
"outputs": [
"speech"
]
},
{
"id": "elevenlabs/eleven-turbo-v2",
"name": "Eleven Turbo v2",
"description": "Eleven Turbo v2 is an English-only, low-latency text-to-speech model from ElevenLabs. It is suited for developer use cases where speed matters and only English is needed, and has a 30,000-character...",
"owned_by": "elevenlabs",
"outputs": [
"speech"
]
},
{
"id": "elevenlabs/eleven-turbo-v2.5",
"name": "Eleven Turbo v2.5",
"description": "Eleven Turbo v2.5 is a low-latency text-to-speech model from ElevenLabs. It balances quality and speed for developer use cases that need non-English languages, supports 32 languages, and has a 40,000-character...",
"owned_by": "elevenlabs",
"outputs": [
"speech"
]
},
{
"id": "elevenlabs/eleven-v3",
"name": "Eleven v3",
"description": "Eleven v3 is a text-to-speech model from ElevenLabs. It produces emotionally rich, highly expressive speech with inline audio tags, supports 70+ languages, and has a 5,000-character request limit.",
"owned_by": "elevenlabs",
"outputs": [
"speech"
]
},
{
"id": "elevenlabs/eleven-v3-conversational",
"name": "Eleven v3 Conversational",
"description": "Eleven v3 Conversational is a text-to-speech model from ElevenLabs, a variant of Eleven v3 optimized for natural dialogue in conversational agents. It supports 70+ languages and has a 5,000-character request...",
"owned_by": "elevenlabs",
"outputs": [
"speech"
]
},
{
"id": "elevenlabs/eleven-v4",
"name": "Eleven v4",
"description": "Eleven v4 is a text-to-speech model from ElevenLabs. It is ElevenLabs' most expressive model, with inline audio tags for emotional and delivery control, support for 90+ languages, and a 10,000-character...",
"owned_by": "elevenlabs",
"outputs": [
"speech"
]
},
{
"id": "elevenlabs/eleven-v4-turbo",
"name": "Eleven v4 Turbo",
"description": "Eleven v4 Turbo is a low-latency text-to-speech model from ElevenLabs. It keeps Eleven v4's expressive delivery and audio tags while being tuned for faster generation, with support for 90+ languages...",
"owned_by": "elevenlabs",
"outputs": [
"speech"
]
},
{
"id": "elorian/glimpse",
"name": "Glimpse",
"description": "Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...",
"owned_by": "elorian",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "enso",
"name": "Enso",
"description": "Routes each request to one tier by the reasoning depth it asks for: enso-flash at off, none, minimal, low, default; enso-pro at medium, high; enso-ultra at xhigh, max. It bills at the price of the tier that answers; the price shown is a request's that states no depth. When nothing pays for that tier it answers on enso-free, at no charge, and says so.",
"owned_by": "hanzo",
"family": "enso",
"context_window": 900000,
"outputs": [
"text"
]
},
{
"id": "enso-auto",
"name": "Enso",
"description": "Routes each request to one tier by the reasoning depth it asks for: enso-flash at off, none, minimal, low, default; enso-pro at medium, high; enso-ultra at xhigh, max. It bills at the price of the tier that answers; the price shown is a request's that states no depth. When nothing pays for that tier it answers on enso-free, at no charge, and says so.",
"owned_by": "hanzo",
"family": "enso",
"context_window": 900000,
"outputs": [
"text"
]
},
{
"id": "enso-flash",
"owned_by": "hanzo",
"family": "enso",
"context_window": 900000,
"outputs": [
"text"
]
},
{
"id": "enso-free",
"owned_by": "hanzo",
"family": "enso",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "enso-pro",
"owned_by": "hanzo",
"family": "enso",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "enso-ultra",
"owned_by": "hanzo",
"family": "enso",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "fireworks/ember-1",
"name": "Ember-1",
"description": "Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...",
"owned_by": "fireworks",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "fish-audio/drama-3",
"name": "Drama 3",
"description": "Drama 3 is a text-to-speech model from Fish Audio built for directed voice performances. You write the direction in plain language in square brackets before a line, such as `[nervous,...",
"owned_by": "fish-audio",
"outputs": [
"speech"
]
},
{
"id": "fish-audio/s1",
"name": "S1",
"description": "S1 is a multilingual text-to-speech model from Fish Audio. It is suited for voice applications that need broad emotional expression, using parenthetical controls to guide speaking style across its supported...",
"owned_by": "fish-audio",
"outputs": [
"speech"
]
},
{
"id": "fish-audio/s2-pro",
"name": "S2 Pro",
"description": "S2 Pro is a multilingual text-to-speech model from Fish Audio. It is suited for expressive narration and multi-speaker dialogue, with natural-language controls for speaking style and emotion.",
"owned_by": "fish-audio",
"outputs": [
"speech"
]
},
{
"id": "fish-audio/s2.1-pro",
"name": "S2.1 Pro",
"description": "S2.1 Pro is a production-oriented text-to-speech model from Fish Audio. It is suited for multilingual voice applications, expressive narration, and dialogue synthesis, with open-ended natural-language controls for speaking style and...",
"owned_by": "fish-audio",
"outputs": [
"speech"
]
},
{
"id": "fish-audio/s2.1-pro-free:free",
"name": "S2.1 Pro Free (free)",
"description": "S2.1 Pro Free is the no-cost variant of Fish Audio S2.1 Pro, intended for testing, prototyping, and low-volume applications. It provides the same synthesis capabilities without production latency or availability...",
"owned_by": "fish-audio",
"outputs": [
"speech"
]
},
{
"id": "free",
"owned_by": "hanzo",
"family": "enso",
"context_window": 65536,
"outputs": [
"text"
]
},
{
"id": "google/gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"description": "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-2.5-flash-image",
"name": "Nano Banana (Gemini 2.5 Flash Image)",
"description": "Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...",
"owned_by": "google",
"context_window": 32768,
"outputs": [
"image",
"text"
]
},
{
"id": "google/gemini-2.5-flash-lite",
"name": "Gemini 2.5 Flash Lite",
"description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-2.5-pro-preview",
"name": "Gemini 2.5 Pro Preview 06-05",
"description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3-flash-preview",
"name": "Gemini 3 Flash Preview",
"description": "Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3-flash-preview:batch",
"name": "Gemini 3 Flash Preview (batch)",
"description": "Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3-pro-image",
"name": "Nano Banana Pro (Gemini 3 Pro Image)",
"description": "Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...",
"owned_by": "google",
"context_window": 131072,
"outputs": [
"image",
"text"
]
},
{
"id": "google/gemini-3-pro-image-preview",
"name": "Nano Banana Pro (Gemini 3 Pro Image Preview)",
"description": "Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...",
"owned_by": "google",
"context_window": 65536,
"outputs": [
"image",
"text"
]
},
{
"id": "google/gemini-3.1-flash-image",
"name": "Nano Banana 2 (Gemini 3.1 Flash Image)",
"description": "Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...",
"owned_by": "google",
"context_window": 131072,
"outputs": [
"image",
"text"
]
},
{
"id": "google/gemini-3.1-flash-image-preview",
"name": "Nano Banana 2 (Gemini 3.1 Flash Image Preview)",
"description": "Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...",
"owned_by": "google",
"context_window": 65536,
"outputs": [
"image",
"text"
]
},
{
"id": "google/gemini-3.1-flash-lite",
"name": "Gemini 3.1 Flash Lite",
"description": "Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3.1-flash-lite-image",
"name": "Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)",
"description": "Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...",
"owned_by": "google",
"context_window": 65536,
"outputs": [
"image",
"text"
]
},
{
"id": "google/gemini-3.1-flash-lite-preview",
"name": "Gemini 3.1 Flash Lite Preview",
"description": "Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3.1-flash-lite:batch",
"name": "Gemini 3.1 Flash Lite (batch)",
"description": "Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3.1-flash-tts-preview",
"name": "Gemini 3.1 Flash TTS Preview",
"description": "Gemini 3.1 Flash TTS Preview is a text-to-speech model from Google, and a substantial generational step up from Gemini 2.5 Flash TTS. It takes text input and produces audio output...",
"owned_by": "google",
"outputs": [
"speech"
]
},
{
"id": "google/gemini-3.1-pro-preview",
"name": "Gemini 3.1 Pro Preview",
"description": "Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3.1-pro-preview-customtools",
"name": "Gemini 3.1 Pro Preview Custom Tools",
"description": "Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3.1-pro-preview:batch",
"name": "Gemini 3.1 Pro Preview (batch)",
"description": "Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3.5-flash",
"name": "Gemini 3.5 Flash",
"description": "Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3.5-flash-lite",
"name": "Gemini 3.5 Flash Lite",
"description": "Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3.5-flash-lite:batch",
"name": "Gemini 3.5 Flash Lite (batch)",
"description": "Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3.5-flash:batch",
"name": "Gemini 3.5 Flash (batch)",
"description": "Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3.6-flash",
"name": "Gemini 3.6 Flash",
"description": "Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3.6-flash:batch",
"name": "Gemini 3.6 Flash (batch)",
"description": "Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3.7-flash",
"name": "Gemini 3.7 Flash",
"description": "Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3.7-flash:batch",
"name": "Gemini 3.7 Flash (batch)",
"description": "Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3.8-flash",
"name": "Gemini 3.8 Flash",
"description": "Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-3.8-flash-lite-tts",
"name": "Gemini 3.8 Flash Lite TTS",
"description": "Gemini 3.8 Flash Lite TTS is a text-to-speech model from Google and the fast, high-throughput member of the 3.8 TTS family alongside [Gemini 3.8 Flash TTS](https://openrouter.ai/google/gemini-3.8-flash-tts). It is suited for...",
"owned_by": "google",
"outputs": [
"speech"
]
},
{
"id": "google/gemini-3.8-flash-tts",
"name": "Gemini 3.8 Flash TTS",
"description": "Gemini 3.8 Flash TTS is a text-to-speech model from Google and the successor to [Gemini 3.1 Flash TTS Preview](https://openrouter.ai/google/gemini-3.1-flash-tts-preview). It is the creative tier of the 3.8 TTS family, suited...",
"owned_by": "google",
"outputs": [
"speech"
]
},
{
"id": "google/gemini-3.8-flash:batch",
"name": "Gemini 3.8 Flash (batch)",
"description": "Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-4-argon",
"name": "Gemini 4 Argon",
"description": "Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-4-argon:batch",
"name": "Gemini 4 Argon (batch)",
"description": "Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "google/gemini-nano-banana-2.1",
"name": "Nano Banana 2.1",
"description": "Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...",
"owned_by": "google",
"context_window": 65536,
"outputs": [
"image",
"text"
]
},
{
"id": "google/gemma-2-27b-it",
"name": "Gemma 2 27B",
"description": "Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...",
"owned_by": "google",
"context_window": 8192,
"outputs": [
"text"
]
},
{
"id": "google/gemma-3-12b-it",
"name": "Gemma 3 12B",
"description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...",
"owned_by": "google",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "google/gemma-3-27b-it",
"name": "Gemma 3 27B",
"description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...",
"owned_by": "google",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "google/gemma-3-4b-it",
"name": "Gemma 3 4B",
"description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...",
"owned_by": "google",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "google/gemma-4-26b-a4b-it",
"name": "Gemma 4 26B A4B",
"description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...",
"owned_by": "google",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "google/gemma-4-26b-a4b-it:free",
"name": "Gemma 4 26B A4B (free)",
"description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...",
"owned_by": "google",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "google/gemma-4-31b-it",
"name": "Gemma 4 31B",
"description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...",
"owned_by": "google",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "google/gemma-4-31b-it:free",
"name": "Gemma 4 31B (free)",
"description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...",
"owned_by": "google",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "google/lyria-3-clip-preview",
"name": "Lyria 3 Clip Preview",
"description": "30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text",
"audio"
]
},
{
"id": "google/lyria-3-pro-preview",
"name": "Lyria 3 Pro Preview",
"description": "Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...",
"owned_by": "google",
"context_window": 1048576,
"outputs": [
"text",
"audio"
]
},
{
"id": "google/veo-3.1",
"name": "Veo 3.1",
"description": "Google's state-of-the-art video generation model, built for maximum visual fidelity in final production cuts. Veo 3.1 generates high-quality 1080p video from text or image prompts with native synchronized audio —...",
"owned_by": "google",
"outputs": [
"video"
]
},
{
"id": "google/veo-3.1-fast",
"name": "Veo 3.1 Fast",
"description": "Google's mid-tier video generation model balancing speed and quality. Veo 3.1 Fast generates high-quality video from text or image prompts with native synchronized audio, offering faster turnaround than Veo 3.1...",
"owned_by": "google",
"outputs": [
"video"
]
},
{
"id": "google/veo-3.1-lite",
"name": "Veo 3.1 Lite",
"description": "Google's most cost-effective video generation model, designed for high-volume applications and rapid iteration. Veo 3.1 Lite generates 720p and 1080p video from text or image prompts with native synchronized audio...",
"owned_by": "google",
"outputs": [
"video"
]
},
{
"id": "gryphe/mythomax-l2-13b",
"name": "MythoMax 13B",
"description": "One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge",
"owned_by": "gryphe",
"context_window": 8192,
"outputs": [
"text"
]
},
{
"id": "hanzo/enso",
"name": "Enso",
"description": "Routes each request to one tier by the reasoning depth it asks for: enso-flash at off, none, minimal, low, default; enso-pro at medium, high; enso-ultra at xhigh, max. It bills at the price of the tier that answers; the price shown is a request's that states no depth. When nothing pays for that tier it answers on enso-free, at no charge, and says so.",
"owned_by": "hanzo",
"family": "enso",
"context_window": 900000,
"outputs": [
"text"
]
},
{
"id": "hanzo/kai",
"name": "Kai 1.7",
"description": "Hanzo's decision model, which answers typed questions at /v1/decisions rather than a chat turn.",
"owned_by": "hanzo",
"family": "kai",
"outputs": [
"decision"
]
},
{
"id": "hanzo/zen",
"owned_by": "zenlm",
"family": "zen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "hexgrad/kokoro-82m",
"name": "Kokoro 82M",
"description": "Kokoro 82M is a lightweight, open-weight text-to-speech model from hexgrad. It converts text to speech across 8 languages (American and British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese)...",
"owned_by": "hexgrad",
"outputs": [
"speech"
]
},
{
"id": "heygen/heygen-video-1",
"name": "HeyGen Video",
"description": "HeyGen Video is a general-purpose video generation model from HeyGen. It renders short clips with synthesized audio (dialogue, ambience, and sound effects) in a single call, working from a text...",
"owned_by": "heygen",
"outputs": [
"video"
]
},
{
"id": "heygen/heygen-voice-1",
"name": "HeyGen Voice",
"description": "HeyGen Voice is a text-to-speech model from HeyGen. It comes with 10 default voices, or bring your own HeyGen key to use voice clones from your own account. It streams...",
"owned_by": "heygen",
"outputs": [
"speech"
]
},
{
"id": "heygen/heygen-voice-1-turbo",
"name": "HeyGen Voice Turbo",
"description": "HeyGen Voice Turbo is a lower-latency version of HeyGen Voice, HeyGen's text-to-speech model. It has the same 10 default voices, or bring your own HeyGen key to use voice clones...",
"owned_by": "heygen",
"outputs": [
"speech"
]
},
{
"id": "heygen/heygen-voice-1-turbo:free",
"name": "HeyGen Voice Turbo (free)",
"description": "HeyGen Voice Turbo is a lower-latency version of HeyGen Voice, HeyGen's text-to-speech model. It has the same 10 default voices, or bring your own HeyGen key to use voice clones...",
"owned_by": "heygen",
"outputs": [
"speech"
]
},
{
"id": "ibm-granite/granite-4.2-8b",
"name": "Granite 4.2 8B",
"description": "Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...",
"owned_by": "ibm-granite",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "inception/mercury-2",
"name": "Mercury 2",
"description": "Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...",
"owned_by": "inception",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "inception/mercury-2.5",
"name": "Mercury 2.5",
"description": "Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...",
"owned_by": "inception",
"context_window": 260000,
"outputs": [
"text"
]
},
{
"id": "inception/mercury-3",
"name": "Mercury 3",
"description": "Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...",
"owned_by": "inception",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "inclusionai/ling-3.0-flash",
"name": "Ling 3.0 Flash",
"description": "*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...",
"owned_by": "inclusionai",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "inclusionai/ling-3.0-flash-vl",
"name": "Ling 3.0 Flash VL",
"description": "Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...",
"owned_by": "inclusionai",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "inclusionai/ling-3.1-flash",
"name": "Ling 3.1 Flash",
"description": "Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.",
"owned_by": "inclusionai",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "inference-net/schematron-v2-small",
"name": "Schematron V2 Small",
"description": "Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...",
"owned_by": "inference-net",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "inference-net/schematron-v2-turbo",
"name": "Schematron V2 Turbo",
"description": "Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...",
"owned_by": "inference-net",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "kai",
"name": "Kai 1.7",
"description": "Hanzo's decision model, which answers typed questions at /v1/decisions rather than a chat turn.",
"owned_by": "hanzo",
"family": "kai",
"outputs": [
"decision"
]
},
{
"id": "kai-1.8",
"name": "Kai 1.7",
"description": "Hanzo's decision model, which answers typed questions at /v1/decisions rather than a chat turn.",
"owned_by": "hanzo",
"family": "kai",
"outputs": [
"decision"
]
},
{
"id": "kwaivgi/kling-v3.0-pro",
"name": "Video v3.0 Pro",
"description": "Kling v3.0 Pro is Kuaishou's premium video generation model, offering higher visual quality than the Standard tier. It supports text-to-video and image-to-video workflows, with first-frame and last-frame control for precise...",
"owned_by": "kwaivgi",
"outputs": [
"video"
]
},
{
"id": "kwaivgi/kling-v3.0-std",
"name": "Video v3.0 Standard",
"description": "Kling v3.0 Standard is a video generation model from Kuaishou. It supports text-to-video and image-to-video workflows, with first-frame and last-frame control for guided scene composition. Clips range from 3 to...",
"owned_by": "kwaivgi",
"outputs": [
"video"
]
},
{
"id": "kwaivgi/kling-video-o1",
"name": "Video O1",
"description": "Kling Video O1 is a video generation model from Kuaishou. It supports text and image inputs with video output, enabling text-to-video and image-to-video workflows. It is suited for cinematic content...",
"owned_by": "kwaivgi",
"outputs": [
"video"
]
},
{
"id": "liquid/lfm-2.5-2.6b",
"name": "LFM2.5-2.6B",
"description": "LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...",
"owned_by": "liquid",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "liquid/lfm-2.5-2.6b:free",
"name": "LFM2.5-2.6B (free)",
"description": "LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...",
"owned_by": "liquid",
"context_window": 65536,
"outputs": [
"text"
]
},
{
"id": "liquid/lfm-2.5-24b-a2b",
"name": "LFM2.5-24B-A2B",
"description": "LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...",
"owned_by": "liquid",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "mancer/weaver",
"name": "Weaver (alpha)",
"description": "An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.",
"owned_by": "mancer",
"context_window": 8000,
"outputs": [
"text"
]
},
{
"id": "meituan/longcat-2.0",
"name": "LongCat 2.0",
"description": "LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...",
"owned_by": "meituan",
"context_window": 1048756,
"outputs": [
"text"
]
},
{
"id": "meta-llama/llama-3.1-70b-instruct",
"name": "Llama 3.1 70B Instruct",
"description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...",
"owned_by": "meta-llama",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "meta-llama/llama-3.1-8b-instruct",
"name": "Llama 3.1 8B Instruct",
"description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...",
"owned_by": "meta-llama",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "meta-llama/llama-3.2-1b-instruct",
"name": "Llama 3.2 1B Instruct",
"description": "Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...",
"owned_by": "meta-llama",
"context_window": 60000,
"outputs": [
"text"
]
},
{
"id": "meta-llama/llama-3.2-3b-instruct",
"name": "Llama 3.2 3B Instruct",
"description": "Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...",
"owned_by": "meta-llama",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "meta-llama/llama-3.3-70b-instruct",
"name": "Llama 3.3 70B Instruct",
"description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...",
"owned_by": "meta-llama",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "meta-llama/llama-4-maverick",
"name": "Llama 4 Maverick",
"description": "Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...",
"owned_by": "meta-llama",
"context_window": 524288,
"outputs": [
"text"
]
},
{
"id": "meta-llama/llama-4-scout",
"name": "Llama 4 Scout",
"description": "Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...",
"owned_by": "meta-llama",
"context_window": 1310720,
"outputs": [
"text"
]
},
{
"id": "meta-llama/llama-guard-4-12b",
"name": "Llama Guard 4 12B",
"description": "Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...",
"owned_by": "meta-llama",
"context_window": 163840,
"outputs": [
"text"
]
},
{
"id": "meta/muse-glimmer-30b",
"name": "Muse Glimmer 30B",
"description": "Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...",
"owned_by": "meta",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "meta/muse-spark-1.1",
"name": "Muse Spark 1.1",
"description": "Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window....",
"owned_by": "meta",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "meta/muse-spark-1.2",
"name": "Muse Spark 1.2",
"description": "Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....",
"owned_by": "meta",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "meta/muse-spark-1.2-contributor",
"name": "Muse Spark 1.2 Contributor",
"description": "Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...",
"owned_by": "meta",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "meta/muse-spark-1.3",
"name": "Muse Spark 1.3",
"description": "Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...",
"owned_by": "meta",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "meta/muse-spark-1.3-contributor",
"name": "Muse Spark 1.3 Contributor",
"description": "Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...",
"owned_by": "meta",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "meta/muse-spark-open",
"name": "Muse Spark Open",
"description": "Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...",
"owned_by": "meta",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "meta/muse-wonder",
"name": "Muse Wonder",
"description": "Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...",
"owned_by": "meta",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "microsoft/mai-voice-2",
"name": "MAI-Voice-2",
"description": "MAI-Voice-2 is an expressive text-to-speech model from Microsoft AI. It is suited for conversational assistants, media narration, accessibility, education, and other long-form voice applications. It supports 15 languages across 18...",
"owned_by": "microsoft",
"outputs": [
"speech"
]
},
{
"id": "microsoft/mai-voice-2-flash",
"name": "MAI-Voice-2-Flash",
"description": "MAI-Voice-2-Flash is a low-latency text-to-speech model from Microsoft AI for voice agents, assistants, call centers, accessibility, narration, and other interactive applications. It generates expressive 24 kHz mono speech across 15...",
"owned_by": "microsoft",
"outputs": [
"speech"
]
},
{
"id": "microsoft/mai-voice-2.1",
"name": "MAI-Voice-2.1",
"description": "MAI-Voice-2.1 is Microsoft AI's highest-fidelity, most expressive text-to-speech model. It produces natural, studio-grade speech across 23 languages, with detailed prosody, nuanced expressiveness, and speaker consistency over long-form content. It is...",
"owned_by": "microsoft",
"outputs": [
"speech"
]
},
{
"id": "microsoft/mai-voice-2.1-flash",
"name": "MAI-Voice-2.1-Flash",
"description": "MAI-Voice-2.1-Flash is a low-latency text-to-speech model from Microsoft AI, optimized for real-time responsiveness. It produces natural, expressive speech across 23 languages, with human-like intonation, rhythm, and emotional nuance. It is...",
"owned_by": "microsoft",
"outputs": [
"speech"
]
},
{
"id": "microsoft/phi-4",
"name": "Phi 4",
"description": "[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...",
"owned_by": "microsoft",
"context_window": 16384,
"outputs": [
"text"
]
},
{
"id": "minimax/hailuo-2.3",
"name": "Hailuo 2.3",
"description": "Hailuo 2.3 is a video generation model from MiniMax. It accepts text prompts and reference images as input and generates video output, supporting both text-to-video and image-to-video workflows. It is...",
"owned_by": "minimax",
"outputs": [
"video"
]
},
{
"id": "minimax/hailuo-3",
"name": "H3",
"description": "MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering, and...",
"owned_by": "minimax",
"outputs": [
"video"
]
},
{
"id": "minimax/hailuo-3-max",
"name": "H3 Max",
"description": "MiniMax H3 Max is a video-generation model from MiniMax, jointly released with fal.ai. Derived through additional training from MiniMax H3, it is designed for faster text-to-video and image-to-video generation with...",
"owned_by": "minimax",
"outputs": [
"video"
]
},
{
"id": "minimax/minimax-01",
"name": "MiniMax-01",
"description": "MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...",
"owned_by": "minimax",
"context_window": 1000192,
"outputs": [
"text"
]
},
{
"id": "minimax/minimax-m1",
"name": "MiniMax M1",
"description": "MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it...",
"owned_by": "minimax",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "minimax/minimax-m2",
"name": "MiniMax M2",
"description": "MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...",
"owned_by": "minimax",
"context_window": 204800,
"outputs": [
"text"
]
},
{
"id": "minimax/minimax-m2-her",
"name": "MiniMax M2-her",
"description": "MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...",
"owned_by": "minimax",
"context_window": 65536,
"outputs": [
"text"
]
},
{
"id": "minimax/minimax-m2.1",
"name": "MiniMax M2.1",
"description": "MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...",
"owned_by": "minimax",
"context_window": 204800,
"outputs": [
"text"
]
},
{
"id": "minimax/minimax-m2.5",
"name": "MiniMax M2.5",
"description": "MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...",
"owned_by": "minimax",
"context_window": 204800,
"outputs": [
"text"
]
},
{
"id": "minimax/minimax-m2.7",
"name": "MiniMax M2.7",
"description": "MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...",
"owned_by": "minimax",
"context_window": 204800,
"outputs": [
"text"
]
},
{
"id": "minimax/minimax-m3",
"name": "MiniMax M3",
"description": "MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...",
"owned_by": "minimax",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "minimax/minimax-m3.1-flash",
"name": "MiniMax M3.1 Flash",
"description": "MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...",
"owned_by": "minimax",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "minimax/speech-2.8-hd",
"name": "Speech 2.8 HD",
"description": "MiniMax Speech 2.8 HD is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.",
"owned_by": "minimax",
"outputs": [
"speech"
]
},
{
"id": "minimax/speech-2.8-turbo",
"name": "Speech 2.8 Turbo",
"description": "MiniMax Speech 2.8 Turbo is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.",
"owned_by": "minimax",
"outputs": [
"speech"
]
},
{
"id": "mistralai/codestral-2508",
"name": "Codestral 2508",
"description": "Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)",
"owned_by": "mistralai",
"context_window": 256000,
"outputs": [
"text"
]
},
{
"id": "mistralai/devstral-2512",
"name": "Devstral 2 2512",
"description": "Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...",
"owned_by": "mistralai",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "mistralai/ministral-14b-2512",
"name": "Ministral 3 14B 2512",
"description": "The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...",
"owned_by": "mistralai",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "mistralai/ministral-3b-2512",
"name": "Ministral 3 3B 2512",
"description": "The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.",
"owned_by": "mistralai",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "mistralai/ministral-8b-2512",
"name": "Ministral 3 8B 2512",
"description": "A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.",
"owned_by": "mistralai",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "mistralai/mistral-large",
"name": "Mistral Large",
"description": "This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....",
"owned_by": "mistralai",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "mistralai/mistral-large-2407",
"name": "Mistral Large 2407",
"description": "This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....",
"owned_by": "mistralai",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "mistralai/mistral-large-2512",
"name": "Mistral Large 3 2512",
"description": "Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.",
"owned_by": "mistralai",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "mistralai/mistral-large-4-0",
"name": "Mistral Large 4",
"description": "Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...",
"owned_by": "mistralai",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "mistralai/mistral-medium-3",
"name": "Mistral Medium 3",
"description": "Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...",
"owned_by": "mistralai",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "mistralai/mistral-medium-3-5",
"name": "Mistral Medium 3.5",
"description": "Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...",
"owned_by": "mistralai",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "mistralai/mistral-medium-3-5:batch",
"name": "Mistral Medium 3.5 (batch)",
"description": "Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...",
"owned_by": "mistralai",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "mistralai/mistral-medium-3.1",
"name": "Mistral Medium 3.1",
"description": "Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...",
"owned_by": "mistralai",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "mistralai/mistral-nemo",
"name": "Mistral Nemo",
"description": "A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...",
"owned_by": "mistralai",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "mistralai/mistral-saba",
"name": "Saba",
"description": "Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...",
"owned_by": "mistralai",
"context_window": 32768,
"outputs": [
"text"
]
},
{
"id": "mistralai/mistral-small-24b-instruct-2501",
"name": "Mistral Small 3",
"description": "Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...",
"owned_by": "mistralai",
"context_window": 32768,
"outputs": [
"text"
]
},
{
"id": "mistralai/mistral-small-2603",
"name": "Mistral Small 4",
"description": "Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...",
"owned_by": "mistralai",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "mistralai/mistral-small-3.1-24b-instruct",
"name": "Mistral Small 3.1 24B",
"description": "Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...",
"owned_by": "mistralai",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "mistralai/mistral-small-3.2-24b-instruct",
"name": "Mistral Small 3.2 24B",
"description": "Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...",
"owned_by": "mistralai",
"context_window": 256000,
"outputs": [
"text"
]
},
{
"id": "mistralai/mixtral-8x22b-instruct",
"name": "Mixtral 8x22B Instruct",
"description": "Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...",
"owned_by": "mistralai",
"context_window": 65536,
"outputs": [
"text"
]
},
{
"id": "mistralai/voxtral-mini-tts-2603",
"name": "Voxtral Mini TTS",
"description": "Voxtral Mini TTS is Mistral's text-to-speech model featuring zero-shot voice cloning and multilingual support. It converts text input into natural-sounding audio output.",
"owned_by": "mistralai",
"outputs": [
"speech"
]
},
{
"id": "mistralai/voxtral-mini-tts-3-0",
"name": "Voxtral TTS 3",
"description": "Voxtral TTS 3 is Mistral's text-to-speech model. It converts text into natural-sounding speech, offers a library of preset voices, supports zero-shot voice cloning, and accepts emotion and pace tags in...",
"owned_by": "mistralai",
"outputs": [
"speech"
]
},
{
"id": "mistralai/voxtral-small-24b-2507",
"name": "Voxtral Small 24B 2507",
"description": "Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...",
"owned_by": "mistralai",
"context_window": 32768,
"outputs": [
"text"
]
},
{
"id": "moondream/moondream3-preview",
"name": "Moondream 3 Preview",
"description": "Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...",
"owned_by": "moondream",
"context_window": 32000,
"outputs": [
"text"
]
},
{
"id": "moondream/moondream3.1-9b-a2b",
"name": "Moondream 3.1",
"description": "Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...",
"owned_by": "moondream",
"context_window": 32000,
"outputs": [
"text"
]
},
{
"id": "moonshotai/kimi-k2",
"name": "Kimi K2 0711",
"description": "Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...",
"owned_by": "moonshotai",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "moonshotai/kimi-k2-0905",
"name": "Kimi K2 0905",
"description": "Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...",
"owned_by": "moonshotai",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "moonshotai/kimi-k2-thinking",
"name": "Kimi K2 Thinking",
"description": "Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...",
"owned_by": "moonshotai",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "moonshotai/kimi-k2.5",
"name": "Kimi K2.5",
"description": "Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...",
"owned_by": "moonshotai",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "moonshotai/kimi-k2.6",
"name": "Kimi K2.6",
"description": "Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...",
"owned_by": "moonshotai",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "moonshotai/kimi-k2.7-code",
"name": "Kimi K2.7 Code",
"description": "MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...",
"owned_by": "moonshotai",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "moonshotai/kimi-k3",
"name": "Kimi K3",
"description": "Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...",
"owned_by": "moonshotai",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "moonshotai/kimi-k3.1-pro",
"name": "Kimi K3.1 Pro",
"description": "Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...",
"owned_by": "moonshotai",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "moonshotai/kimi-k3:batch",
"name": "Kimi K3 (batch)",
"description": "Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...",
"owned_by": "moonshotai",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "morph/morph-v3-fast",
"name": "Morph V3 Fast",
"description": "Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...",
"owned_by": "morph",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "morph/morph-v3-large",
"name": "Morph V3 Large",
"description": "Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...",
"owned_by": "morph",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "nex-agi/nex-n2.5-mini",
"name": "Nex-N2.5-Mini",
"description": "Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...",
"owned_by": "nex-agi",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "nex-agi/nex-n2.5-pro",
"name": "Nex-N2.5-Pro",
"description": "Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...",
"owned_by": "nex-agi",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "nousresearch/hermes-3-llama-3.1-405b",
"name": "Hermes 3 405B Instruct",
"description": "Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...",
"owned_by": "nousresearch",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "nousresearch/hermes-3-llama-3.1-70b",
"name": "Hermes 3 70B Instruct",
"description": "Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...",
"owned_by": "nousresearch",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "nousresearch/hermes-4-405b",
"name": "Hermes 4 405B",
"description": "Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...",
"owned_by": "nousresearch",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "nvidia/nemotron-3-nano-30b-a3b",
"name": "Nemotron 3 Nano 30B A3B",
"description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...",
"owned_by": "nvidia",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
"name": "Nemotron 3 Nano Omni (free)",
"description": "NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...",
"owned_by": "nvidia",
"context_window": 256000,
"outputs": [
"text"
]
},
{
"id": "nvidia/nemotron-3-super-120b-a12b",
"name": "Nemotron 3 Super",
"description": "NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...",
"owned_by": "nvidia",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "nvidia/nemotron-3-super-120b-a12b:free",
"name": "Nemotron 3 Super (free)",
"description": "NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...",
"owned_by": "nvidia",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "nvidia/nemotron-3-ultra-550b-a55b",
"name": "Nemotron 3 Ultra",
"description": "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...",
"owned_by": "nvidia",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "nvidia/nemotron-3-ultra-550b-a55b:free",
"name": "Nemotron 3 Ultra (free)",
"description": "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...",
"owned_by": "nvidia",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "nvidia/nemotron-3.5-content-safety",
"name": "Nemotron 3.5 Content Safety",
"description": "NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...",
"owned_by": "nvidia",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "nvidia/nemotron-3.5-content-safety:free",
"name": "Nemotron 3.5 Content Safety (free)",
"description": "NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...",
"owned_by": "nvidia",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "nvidia/nemotron-3.5-lightning",
"name": "Nemotron 3.5 Lightning",
"description": "NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...",
"owned_by": "nvidia",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "nvidia/nemotron-3.5-lightning:free",
"name": "Nemotron 3.5 Lightning (free)",
"description": "NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...",
"owned_by": "nvidia",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "nvidia/nemotron-3.5-super-vl",
"name": "Nemotron 3.5 Super VL",
"description": "NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...",
"owned_by": "nvidia",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "nvidia/nemotron-3.5-super-vl:free",
"name": "Nemotron 3.5 Super VL (free)",
"description": "NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...",
"owned_by": "nvidia",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "nvidia/switchyard",
"name": "Switchyard",
"description": "Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most...",
"owned_by": "nvidia",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-3.5-turbo-0613",
"name": "GPT-3.5 Turbo (older v0613)",
"description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.",
"owned_by": "openai",
"context_window": 4095,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-3.5-turbo-16k",
"name": "GPT-3.5 Turbo 16k",
"description": "This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...",
"owned_by": "openai",
"context_window": 16385,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-4",
"name": "GPT-4",
"description": "OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...",
"owned_by": "openai",
"context_window": 8191,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-4-turbo",
"name": "GPT-4 Turbo",
"description": "The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.",
"owned_by": "openai",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-4-turbo:batch",
"name": "GPT-4 Turbo (batch)",
"description": "The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.",
"owned_by": "openai",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-4.1",
"name": "GPT-4.1",
"description": "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...",
"owned_by": "openai",
"context_window": 1047576,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-4.1-mini",
"name": "GPT-4.1 Mini",
"description": "GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...",
"owned_by": "openai",
"context_window": 1047576,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-4.1-mini:batch",
"name": "GPT-4.1 Mini (batch)",
"description": "GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...",
"owned_by": "openai",
"context_window": 1047576,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-4.1-nano",
"name": "GPT-4.1 Nano",
"description": "For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...",
"owned_by": "openai",
"context_window": 1047576,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-4.1-nano:batch",
"name": "GPT-4.1 Nano (batch)",
"description": "For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...",
"owned_by": "openai",
"context_window": 1047576,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-4.1:batch",
"name": "GPT-4.1 (batch)",
"description": "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...",
"owned_by": "openai",
"context_window": 1047576,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-4o",
"name": "GPT-4o",
"description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...",
"owned_by": "openai",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-4o-2024-05-13",
"name": "GPT-4o (2024-05-13)",
"description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...",
"owned_by": "openai",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-4o-2024-08-06",
"name": "GPT-4o (2024-08-06)",
"description": "The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o (\"o\" for \"omni\") is...",
"owned_by": "openai",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-4o-2024-11-20",
"name": "GPT-4o (2024-11-20)",
"description": "The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...",
"owned_by": "openai",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-4o-mini",
"name": "GPT-4o-mini",
"description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...",
"owned_by": "openai",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-4o-mini-2024-07-18",
"name": "GPT-4o-mini (2024-07-18)",
"description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...",
"owned_by": "openai",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-4o-mini:batch",
"name": "GPT-4o-mini (batch)",
"description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...",
"owned_by": "openai",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-4o:batch",
"name": "GPT-4o (batch)",
"description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...",
"owned_by": "openai",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5",
"name": "GPT-5",
"description": "GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5-image",
"name": "GPT-5 Image",
"description": "[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"image",
"text"
]
},
{
"id": "openai/gpt-5-image-mini",
"name": "GPT-5 Image Mini",
"description": "GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"image",
"text"
]
},
{
"id": "openai/gpt-5-mini",
"name": "GPT-5 Mini",
"description": "GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5-mini:batch",
"name": "GPT-5 Mini (batch)",
"description": "GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5-nano",
"name": "GPT-5 Nano",
"description": "GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5-nano:batch",
"name": "GPT-5 Nano (batch)",
"description": "GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5-pro",
"name": "GPT-5 Pro",
"description": "GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5-pro:batch",
"name": "GPT-5 Pro (batch)",
"description": "GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.1",
"name": "GPT-5.1",
"description": "GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.1-codex",
"name": "GPT-5.1-Codex",
"description": "GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.1-codex-max",
"name": "GPT-5.1-Codex-Max",
"description": "GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.1-codex-mini",
"name": "GPT-5.1-Codex-Mini",
"description": "GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.1:batch",
"name": "GPT-5.1 (batch)",
"description": "GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.2",
"name": "GPT-5.2",
"description": "GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.2-chat",
"name": "GPT-5.2 Chat",
"description": "GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...",
"owned_by": "openai",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.2-codex",
"name": "GPT-5.2-Codex",
"description": "GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.2-pro",
"name": "GPT-5.2 Pro",
"description": "GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.2-pro:batch",
"name": "GPT-5.2 Pro (batch)",
"description": "GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.2:batch",
"name": "GPT-5.2 (batch)",
"description": "GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.3-codex",
"name": "GPT-5.3-Codex",
"description": "GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.4",
"name": "GPT-5.4",
"description": "GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.4-image-2",
"name": "GPT-5.4 Image 2",
"description": "[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...",
"owned_by": "openai",
"context_window": 272000,
"outputs": [
"image",
"text"
]
},
{
"id": "openai/gpt-5.4-mini",
"name": "GPT-5.4 Mini",
"description": "GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.4-mini:batch",
"name": "GPT-5.4 Mini (batch)",
"description": "GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.4-nano",
"name": "GPT-5.4 Nano",
"description": "GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.4-nano:batch",
"name": "GPT-5.4 Nano (batch)",
"description": "GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.4-pro",
"name": "GPT-5.4 Pro",
"description": "GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.4-pro:batch",
"name": "GPT-5.4 Pro (batch)",
"description": "GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.4:batch",
"name": "GPT-5.4 (batch)",
"description": "GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.5",
"name": "GPT-5.5",
"description": "GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.5-pro",
"name": "GPT-5.5 Pro",
"description": "GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.5-pro:batch",
"name": "GPT-5.5 Pro (batch)",
"description": "GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.5:batch",
"name": "GPT-5.5 (batch)",
"description": "GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.6-luna",
"name": "GPT-5.6 Luna",
"description": "GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.6-luna-pro",
"name": "GPT-5.6 Luna Pro",
"description": "GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.6-luna-pro:batch",
"name": "GPT-5.6 Luna Pro (batch)",
"description": "GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.6-luna:batch",
"name": "GPT-5.6 Luna (batch)",
"description": "GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.6-sol",
"name": "GPT-5.6 Sol",
"description": "GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.6-sol-pro",
"name": "GPT-5.6 Sol Pro",
"description": "GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.6-sol-pro:batch",
"name": "GPT-5.6 Sol Pro (batch)",
"description": "GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.6-sol:batch",
"name": "GPT-5.6 Sol (batch)",
"description": "GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.6-terra",
"name": "GPT-5.6 Terra",
"description": "GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.6-terra-pro",
"name": "GPT-5.6 Terra Pro",
"description": "GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.6-terra-pro:batch",
"name": "GPT-5.6 Terra Pro (batch)",
"description": "GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5.6-terra:batch",
"name": "GPT-5.6 Terra (batch)",
"description": "GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-5:batch",
"name": "GPT-5 (batch)",
"description": "GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6-astra",
"name": "GPT-6 Astra",
"description": "GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6-astra-pro",
"name": "GPT-6 Astra Pro",
"description": "GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6-astra-pro:batch",
"name": "GPT-6 Astra Pro (batch)",
"description": "GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6-astra:batch",
"name": "GPT-6 Astra (batch)",
"description": "GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6-luna",
"name": "GPT-6 Luna",
"description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6-luna-pro",
"name": "GPT-6 Luna Pro",
"description": "GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6-luna-pro:batch",
"name": "GPT-6 Luna Pro (batch)",
"description": "GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6-luna:batch",
"name": "GPT-6 Luna (batch)",
"description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6-sol",
"name": "GPT-6 Sol",
"description": "GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6-sol-pro",
"name": "GPT-6 Sol Pro",
"description": "GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6-sol-pro:batch",
"name": "GPT-6 Sol Pro (batch)",
"description": "GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6-sol:batch",
"name": "GPT-6 Sol (batch)",
"description": "GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6.1-sol",
"name": "GPT-6.1 Sol",
"description": "GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6.1-sol-pro",
"name": "GPT-6.1 Sol Pro",
"description": "GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6.1-sol-pro:batch",
"name": "GPT-6.1 Sol Pro (batch)",
"description": "GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6.1-sol:batch",
"name": "GPT-6.1 Sol (batch)",
"description": "GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6.1-terra",
"name": "GPT-6.1 Terra",
"description": "GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6.1-terra-pro",
"name": "GPT-6.1 Terra Pro",
"description": "GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6.1-terra-pro:batch",
"name": "GPT-6.1 Terra Pro (batch)",
"description": "GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-6.1-terra:batch",
"name": "GPT-6.1 Terra (batch)",
"description": "GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...",
"owned_by": "openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-audio",
"name": "GPT Audio",
"description": "The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...",
"owned_by": "openai",
"context_window": 128000,
"outputs": [
"text",
"audio"
]
},
{
"id": "openai/gpt-audio-mini",
"name": "GPT Audio Mini",
"description": "A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...",
"owned_by": "openai",
"context_window": 128000,
"outputs": [
"text",
"audio"
]
},
{
"id": "openai/gpt-chat-latest",
"name": "GPT Chat Latest",
"description": "GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...",
"owned_by": "openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-oss-120b",
"name": "gpt-oss-120b",
"description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...",
"owned_by": "openai",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-oss-120b:batch",
"name": "gpt-oss-120b (batch)",
"description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...",
"owned_by": "openai",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-oss-20b",
"name": "gpt-oss-20b",
"description": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...",
"owned_by": "openai",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-oss-20b:batch",
"name": "gpt-oss-20b (batch)",
"description": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...",
"owned_by": "openai",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "openai/gpt-oss-safeguard-20b",
"name": "gpt-oss-safeguard-20b",
"description": "gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...",
"owned_by": "openai",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "openai/o1",
"name": "o1",
"description": "The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...",
"owned_by": "openai",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "openai/o1-pro",
"name": "o1-pro",
"description": "The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...",
"owned_by": "openai",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "openai/o3",
"name": "o3",
"description": "o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....",
"owned_by": "openai",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "openai/o3-mini",
"name": "o3 Mini",
"description": "OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...",
"owned_by": "openai",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "openai/o3-mini-high",
"name": "o3 Mini High",
"description": "OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...",
"owned_by": "openai",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "openai/o3-mini:batch",
"name": "o3 Mini (batch)",
"description": "OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...",
"owned_by": "openai",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "openai/o3-pro",
"name": "o3 Pro",
"description": "The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...",
"owned_by": "openai",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "openai/o3:batch",
"name": "o3 (batch)",
"description": "o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....",
"owned_by": "openai",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "openai/o4-mini",
"name": "o4 Mini",
"description": "OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...",
"owned_by": "openai",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "openai/o4-mini-high",
"name": "o4 Mini High",
"description": "OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...",
"owned_by": "openai",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "openai/o4-mini:batch",
"name": "o4 Mini (batch)",
"description": "OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...",
"owned_by": "openai",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "openrouter/auto",
"name": "Auto Router",
"description": "The Auto Router automatically selects the best model for your prompt, powered by the wisdom of the market. It routes you based on what the OpenRouter community collectively spends on...",
"owned_by": "openrouter",
"context_window": 2000000,
"outputs": [
"text",
"image"
]
},
{
"id": "openrouter/auto-beta",
"name": "Auto Router (Beta)",
"description": "The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta...",
"owned_by": "openrouter",
"context_window": 2000000,
"outputs": [
"text",
"image"
]
},
{
"id": "openrouter/bodybuilder",
"name": "Body Builder (beta)",
"description": "Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...",
"owned_by": "openrouter",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "openrouter/free",
"name": "Free Models Router",
"description": "The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...",
"owned_by": "openrouter",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "openrouter/fusion",
"name": "Fusion",
"description": "Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...",
"owned_by": "openrouter",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "openrouter/pareto-code",
"name": "Pareto Code Router",
"description": "The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how...",
"owned_by": "openrouter",
"context_window": 2000000,
"outputs": [
"text"
]
},
{
"id": "perceptron/perceptron-mk1",
"name": "Perceptron Mk1",
"description": "Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...",
"owned_by": "perceptron",
"context_window": 32768,
"outputs": [
"text"
]
},
{
"id": "perceptron/perceptron-mk1.5",
"name": "Perceptron Mk1.5",
"description": "Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...",
"owned_by": "perceptron",
"context_window": 36864,
"outputs": [
"text"
]
},
{
"id": "perplexity/sonar",
"name": "Sonar",
"description": "Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...",
"owned_by": "perplexity",
"context_window": 127072,
"outputs": [
"text"
]
},
{
"id": "perplexity/sonar-deep-research",
"name": "Sonar Deep Research",
"description": "Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...",
"owned_by": "perplexity",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "perplexity/sonar-pro",
"name": "Sonar Pro",
"description": "Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...",
"owned_by": "perplexity",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "perplexity/sonar-pro-search",
"name": "Sonar Pro Search",
"description": "Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...",
"owned_by": "perplexity",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "perplexity/sonar-reasoning-pro",
"name": "Sonar Reasoning Pro",
"description": "Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...",
"owned_by": "perplexity",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "poolside/laguna-s-2.1",
"name": "Laguna S 2.1",
"description": "Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...",
"owned_by": "poolside",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "poolside/laguna-s-2.1:free",
"name": "Laguna S 2.1 (free)",
"description": "Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...",
"owned_by": "poolside",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "poolside/laguna-xs-2.1",
"name": "Laguna XS 2.1",
"description": "Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...",
"owned_by": "poolside",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "poolside/laguna-xs-2.1:free",
"name": "Laguna XS 2.1 (free)",
"description": "Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...",
"owned_by": "poolside",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "prism-ml/ternary-bonsai-2-27b",
"name": "Ternary Bonsai 2 27B",
"description": "Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...",
"owned_by": "prism-ml",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen-2.5-72b-instruct",
"name": "Qwen2.5 72B Instruct",
"description": "Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...",
"owned_by": "qwen",
"context_window": 32768,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen-2.5-7b-instruct",
"name": "Qwen2.5 7B Instruct",
"description": "Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...",
"owned_by": "qwen",
"context_window": 32768,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen-2.5-coder-32b-instruct",
"name": "Qwen2.5 Coder 32B Instruct",
"description": "Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...",
"owned_by": "qwen",
"context_window": 32768,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen-audio-3.0-tts-flash",
"name": "Qwen-Audio-3.0-TTS Flash",
"description": "Qwen-Audio-3.0-TTS Flash is Alibaba's fast, cost-efficient text-to-speech model, generating spoken audio from text via the DashScope Speech Synthesizer API.",
"owned_by": "qwen",
"outputs": [
"speech"
]
},
{
"id": "qwen/qwen-audio-3.0-tts-plus",
"name": "Qwen-Audio-3.0-TTS Plus",
"description": "Qwen-Audio-3.0-TTS Plus is Alibaba's higher-quality text-to-speech model, generating spoken audio from text via the DashScope Speech Synthesizer API.",
"owned_by": "qwen",
"outputs": [
"speech"
]
},
{
"id": "qwen/qwen-plus",
"name": "Qwen-Plus",
"description": "Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.",
"owned_by": "qwen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen2.5-vl-72b-instruct",
"name": "Qwen2.5 VL 72B Instruct",
"description": "Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.",
"owned_by": "qwen",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3-14b",
"name": "Qwen3 14B",
"description": "Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...",
"owned_by": "qwen",
"context_window": 40960,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3-235b-a22b-2507",
"name": "Qwen3 235B A22B Instruct 2507",
"description": "Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3-235b-a22b-thinking-2507",
"name": "Qwen3 235B A22B Thinking 2507",
"description": "Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...",
"owned_by": "qwen",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3-30b-a3b",
"name": "Qwen3 30B A3B",
"description": "Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...",
"owned_by": "qwen",
"context_window": 40960,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3-30b-a3b-instruct-2507",
"name": "Qwen3 30B A3B Instruct 2507",
"description": "Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3-32b",
"name": "Qwen3 32B",
"description": "Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...",
"owned_by": "qwen",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3-coder",
"name": "Qwen3 Coder 480B A35B",
"description": "Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3-coder-30b-a3b-instruct",
"name": "Qwen3 Coder 30B A3B Instruct",
"description": "Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3-coder-flash",
"name": "Qwen3 Coder Flash",
"description": "Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...",
"owned_by": "qwen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3-coder-next",
"name": "Qwen3 Coder Next",
"description": "Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3-next-80b-a3b-instruct",
"name": "Qwen3 Next 80B A3B Instruct",
"description": "Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3-next-80b-a3b-thinking",
"name": "Qwen3 Next 80B A3B Thinking",
"description": "Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3-vl-235b-a22b-instruct",
"name": "Qwen3 VL 235B A22B Instruct",
"description": "Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3-vl-30b-a3b-instruct",
"name": "Qwen3 VL 30B A3B Instruct",
"description": "Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3-vl-30b-a3b-thinking",
"name": "Qwen3 VL 30B A3B Thinking",
"description": "Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3-vl-8b-instruct",
"name": "Qwen3 VL 8B Instruct",
"description": "Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.5-122b-a10b",
"name": "Qwen3.5-122B-A10B",
"description": "The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.5-27b",
"name": "Qwen3.5-27B",
"description": "The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.5-35b-a3b",
"name": "Qwen3.5-35B-A3B",
"description": "The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.5-397b-a17b",
"name": "Qwen3.5 397B A17B",
"description": "The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.5-9b",
"name": "Qwen3.5-9B",
"description": "Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.5-flash-02-23",
"name": "Qwen3.5-Flash",
"description": "The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...",
"owned_by": "qwen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.5-plus-02-15",
"name": "Qwen3.5 Plus 2026-02-15",
"description": "The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...",
"owned_by": "qwen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.5-plus-20260420",
"name": "Qwen3.5 Plus 2026-04-20",
"description": "Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...",
"owned_by": "qwen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.6-27b",
"name": "Qwen3.6 27B",
"description": "Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.6-35b-a3b",
"name": "Qwen3.6 35B A3B",
"description": "Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.6-flash",
"name": "Qwen3.6 Flash",
"description": "Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...",
"owned_by": "qwen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.6-plus",
"name": "Qwen3.6 Plus",
"description": "Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...",
"owned_by": "qwen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.7-flash",
"name": "Qwen3.7 Flash",
"description": "Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...",
"owned_by": "qwen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.7-max",
"name": "Qwen3.7 Max",
"description": "Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...",
"owned_by": "qwen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.7-plus",
"name": "Qwen3.7 Plus",
"description": "Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...",
"owned_by": "qwen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.7-plus:batch",
"name": "Qwen3.7 Plus (batch)",
"description": "Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...",
"owned_by": "qwen",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.8-2.4t-a95b",
"name": "Qwen3.8 2.4T A95B",
"description": "Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...",
"owned_by": "qwen",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.8-27b",
"name": "Qwen3.8 27B",
"description": "Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...",
"owned_by": "qwen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.8-flash",
"name": "Qwen3.8 Flash",
"description": "Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.",
"owned_by": "qwen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.8-max-0902",
"name": "Qwen3.8 Max (0902)",
"description": "Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...",
"owned_by": "qwen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.8-max-prime",
"name": "Qwen3.8 Max Prime",
"description": "Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...",
"owned_by": "qwen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "qwen/qwen3.8-omni-flash",
"name": "Qwen3.8 Omni Flash",
"description": "Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...",
"owned_by": "qwen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "recursive/flint-v1.0:free",
"name": "Flint (free)",
"description": "Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...",
"owned_by": "recursive",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "reflection/beam-1.0-501b-a23b",
"name": "Beam 1.0 501B A23B",
"description": "Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...",
"owned_by": "reflection",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "rekaai/reka-edge",
"name": "Reka Edge",
"description": "Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...",
"owned_by": "rekaai",
"context_window": 16384,
"outputs": [
"text"
]
},
{
"id": "rekaai/reka-flash-3",
"name": "Reka Flash 3",
"description": "Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...",
"owned_by": "rekaai",
"context_window": 65536,
"outputs": [
"text"
]
},
{
"id": "relace/relace-apply-3",
"name": "Relace Apply 3",
"description": "Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...",
"owned_by": "relace",
"context_window": 256000,
"outputs": [
"text"
]
},
{
"id": "relace/relace-search",
"name": "Relace Search",
"description": "The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...",
"owned_by": "relace",
"context_window": 256000,
"outputs": [
"text"
]
},
{
"id": "runway/gen-4.5",
"name": "Gen-4.5",
"description": "Runway Gen-4.5 is a video generation model from Runway for text-to-video and image-to-video workflows. It is designed for cinematic scene creation with strong motion quality, visual fidelity, and prompt adherence....",
"owned_by": "runway",
"outputs": [
"video"
]
},
{
"id": "sakana/fugu-max",
"name": "Fugu Max",
"description": "Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...",
"owned_by": "sakana",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "sakana/fugu-ultra",
"name": "Fugu Ultra",
"description": "Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...",
"owned_by": "sakana",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "sakana/fugu-ultra-v2",
"name": "Fugu Ultra v2",
"description": "Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...",
"owned_by": "sakana",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "sakana/sakana-namazu",
"name": "Sakana Namazu",
"description": "Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...",
"owned_by": "sakana",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "sao10k/l3-lunaris-8b",
"name": "Llama 3 8B Lunaris",
"description": "Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....",
"owned_by": "sao10k",
"context_window": 8192,
"outputs": [
"text"
]
},
{
"id": "sao10k/l3.1-euryale-70b",
"name": "Llama 3.1 Euryale 70B v2.2",
"description": "Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).",
"owned_by": "sao10k",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "scaledown/extract",
"name": "Extract",
"description": "Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...",
"owned_by": "scaledown",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "scaledown/summarize",
"name": "Summarize",
"description": "Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...",
"owned_by": "scaledown",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "sesame/csm-1b",
"name": "CSM 1B",
"description": "CSM 1B is a conversational speech model from Sesame. It accepts text input and produces English speech output, with voice options spanning conversational and read-speech styles. At 1B parameters, it...",
"owned_by": "sesame",
"outputs": [
"speech"
]
},
{
"id": "stepfun/step-3.5-flash",
"name": "Step 3.5 Flash",
"description": "Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....",
"owned_by": "stepfun",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "stepfun/step-3.7-flash",
"name": "Step 3.7 Flash",
"description": "Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...",
"owned_by": "stepfun",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "stepfun/step-5-preview",
"name": "Step 5 Preview",
"description": "Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...",
"owned_by": "stepfun",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "tencent/hunyuan-a13b-instruct",
"name": "Hunyuan A13B Instruct",
"description": "Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...",
"owned_by": "tencent",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "tencent/hy-mt2-1.8b",
"name": "Hy-MT2-1.8B",
"description": "Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...",
"owned_by": "tencent",
"context_window": 8192,
"outputs": [
"text"
]
},
{
"id": "tencent/hy-mt2-30b-a3b",
"name": "Hy-MT2-30B-A3B",
"description": "Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...",
"owned_by": "tencent",
"context_window": 8192,
"outputs": [
"text"
]
},
{
"id": "tencent/hy-mt2-7b",
"name": "Hy-MT2-7B",
"description": "Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.",
"owned_by": "tencent",
"context_window": 8192,
"outputs": [
"text"
]
},
{
"id": "tencent/hy3",
"name": "Hy3",
"description": "Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...",
"owned_by": "tencent",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "tencent/hy3-preview",
"name": "Hy3 preview",
"description": "Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...",
"owned_by": "tencent",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "tencent/hy4-preview",
"name": "Hy4 preview",
"description": "Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...",
"owned_by": "tencent",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "thedrummer/cydonia-24b-v4.1",
"name": "Cydonia 24B V4.1",
"description": "Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.",
"owned_by": "thedrummer",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "thedrummer/skyfall-36b-v2",
"name": "Skyfall 36B V2",
"description": "Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.",
"owned_by": "thedrummer",
"context_window": 32768,
"outputs": [
"text"
]
},
{
"id": "thedrummer/unslopnemo-12b",
"name": "UnslopNemo 12B",
"description": "UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.",
"owned_by": "thedrummer",
"context_window": 1024000,
"outputs": [
"text"
]
},
{
"id": "thinkingmachines/inkling",
"name": "Inkling",
"description": "Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...",
"owned_by": "thinkingmachines",
"context_window": 524288,
"outputs": [
"text"
]
},
{
"id": "thinkingmachines/inkling-small",
"name": "Inkling Small",
"description": "Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...",
"owned_by": "thinkingmachines",
"context_window": 524288,
"outputs": [
"text"
]
},
{
"id": "thinkingmachines/inkling-small:free",
"name": "Inkling Small (free)",
"description": "Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...",
"owned_by": "thinkingmachines",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "thinkingmachines/inkling:free",
"name": "Inkling (free)",
"description": "Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...",
"owned_by": "thinkingmachines",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "typesafe/jev-1.13",
"name": "Jev 1.13",
"owned_by": "typesafe",
"outputs": [
"decision"
]
},
{
"id": "typesafe/jev-router",
"name": "Jev Router",
"description": "Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on [Jev](https://openrouter.ai/~typesafe/jev-latest), TypeSafe's first System One model, and adapts as your...",
"owned_by": "typesafe",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "unbiased/pareto-26.10",
"name": "Pareto 26.10",
"description": "Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.",
"owned_by": "unbiased",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "unbiased/pareto-26.9",
"name": "Pareto 26.9",
"description": "Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.",
"owned_by": "unbiased",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "undi95/remm-slerp-l2-13b",
"name": "ReMM SLERP 13B",
"description": "A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge",
"owned_by": "undi95",
"context_window": 6144,
"outputs": [
"text"
]
},
{
"id": "upstage/solar-mini4",
"name": "Solar Mini 4",
"description": "Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...",
"owned_by": "upstage",
"context_window": 524288,
"outputs": [
"text"
]
},
{
"id": "upstage/solar-pro-3",
"name": "Solar Pro 3",
"description": "Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...",
"owned_by": "upstage",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "upstage/solar-pro4",
"name": "Solar Pro 4",
"description": "Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...",
"owned_by": "upstage",
"context_window": 524288,
"outputs": [
"text"
]
},
{
"id": "writer/palmyra-x5",
"name": "Palmyra X5",
"description": "Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...",
"owned_by": "writer",
"context_window": 1040000,
"outputs": [
"text"
]
},
{
"id": "x-ai/grok-4.20",
"name": "Grok 4.20",
"description": "Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...",
"owned_by": "x-ai",
"context_window": 2000000,
"outputs": [
"text"
]
},
{
"id": "x-ai/grok-4.20-multi-agent",
"name": "Grok 4.20 Multi-Agent",
"description": "Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...",
"owned_by": "x-ai",
"context_window": 2000000,
"outputs": [
"text"
]
},
{
"id": "x-ai/grok-4.3",
"name": "Grok 4.3",
"description": "Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...",
"owned_by": "x-ai",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "x-ai/grok-4.3:batch",
"name": "Grok 4.3 (batch)",
"description": "Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...",
"owned_by": "x-ai",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "x-ai/grok-4.5",
"name": "Grok 4.5",
"description": "Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.",
"owned_by": "x-ai",
"context_window": 500000,
"outputs": [
"text"
]
},
{
"id": "x-ai/grok-4.6",
"name": "Grok 4.6",
"description": "Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).",
"owned_by": "x-ai",
"context_window": 500000,
"outputs": [
"text"
]
},
{
"id": "x-ai/grok-4.7",
"name": "Grok 4.7",
"description": "Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...",
"owned_by": "x-ai",
"context_window": 500000,
"outputs": [
"text"
]
},
{
"id": "x-ai/grok-build-0.1",
"name": "Grok Build 0.1",
"description": "Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...",
"owned_by": "x-ai",
"context_window": 256000,
"outputs": [
"text"
]
},
{
"id": "x-ai/grok-imagine-video",
"name": "Grok Imagine Video",
"description": "Grok Imagine Video is SpaceXAI's fast, text-, image-, and reference-conditioned video generation model. It produces short videos (1–15 seconds, 24 fps) at 480p or 720p across seven aspect ratios -...",
"owned_by": "x-ai",
"outputs": [
"video"
]
},
{
"id": "x-ai/grok-imagine-video-1.5",
"name": "Grok Imagine Video 1.5",
"description": "Grok Imagine Video 1.5 is a video generation model from SpaceXAI. It creates videos from text prompts, with an optional starting image to guide the scene. It can direct subject...",
"owned_by": "x-ai",
"outputs": [
"video"
]
},
{
"id": "x-ai/grok-imagine-video-1.5-lite",
"name": "Grok Imagine Video 1.5 Lite",
"description": "Grok Imagine Video 1.5 Lite is a faster, lower-cost video generation model from SpaceXAI, distilled from [Grok Imagine Video 1.5](/x-ai/grok-imagine-video-1.5). It supports text-to-video and image-to-video, trading some quality for speed...",
"owned_by": "x-ai",
"outputs": [
"video"
]
},
{
"id": "x-ai/grok-voice-tts-1.0",
"name": "Grok Voice TTS 1.0",
"description": "Grok Voice TTS 1.0 is a text-to-speech model from SpaceXAI. It converts text into spoken audio across 20+ languages with automatic language detection, and offers five built-in voices (Eve, Ara,...",
"owned_by": "x-ai",
"outputs": [
"speech"
]
},
{
"id": "xiaomi/mimo-v2.5",
"name": "MiMo-V2.5",
"description": "MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...",
"owned_by": "xiaomi",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "xiaomi/mimo-v2.5-pro",
"name": "MiMo-V2.5-Pro",
"description": "MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....",
"owned_by": "xiaomi",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "xiaomi/mimo-v2.6-flash",
"name": "MiMo-V2.6-Flash",
"description": "MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...",
"owned_by": "xiaomi",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "xiaomi/mimo-v2.6-pro",
"name": "MiMo-V2.6-Pro",
"description": "MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...",
"owned_by": "xiaomi",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "xiaomi/mimo-v2.6-pro-ultraspeed",
"name": "MiMo-V2.6-Pro-UltraSpeed",
"description": "MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x...",
"owned_by": "xiaomi",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "xingchen-agi/xing4.0-29b-a4b:free",
"name": "Xing4.0 29B A4B (free)",
"description": "Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It has 29B total parameters with 4B active per token...",
"owned_by": "xingchen-agi",
"context_window": 262144,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-4.5",
"name": "GLM 4.5",
"description": "GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...",
"owned_by": "z-ai",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-4.5-air",
"name": "GLM 4.5 Air",
"description": "GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...",
"owned_by": "z-ai",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-4.5v",
"name": "GLM 4.5V",
"description": "GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...",
"owned_by": "z-ai",
"context_window": 65536,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-4.6",
"name": "GLM 4.6",
"description": "Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...",
"owned_by": "z-ai",
"context_window": 204800,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-4.6v",
"name": "GLM 4.6V",
"description": "GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...",
"owned_by": "z-ai",
"context_window": 131072,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-4.7",
"name": "GLM 4.7",
"description": "GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...",
"owned_by": "z-ai",
"context_window": 204800,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-4.7-flash",
"name": "GLM 4.7 Flash",
"description": "As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...",
"owned_by": "z-ai",
"context_window": 200000,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-5",
"name": "GLM 5",
"description": "GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...",
"owned_by": "z-ai",
"context_window": 204800,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-5-turbo",
"name": "GLM 5 Turbo",
"description": "GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...",
"owned_by": "z-ai",
"context_window": 202752,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-5.1",
"name": "GLM 5.1",
"description": "GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...",
"owned_by": "z-ai",
"context_window": 204800,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-5.2",
"name": "GLM 5.2",
"description": "GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...",
"owned_by": "z-ai",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-5.3",
"name": "GLM 5.3",
"description": "GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...",
"owned_by": "z-ai",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-5.3-flash",
"name": "GLM 5.3 Flash",
"description": "GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...",
"owned_by": "z-ai",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-5.3-flash:batch",
"name": "GLM 5.3 Flash (batch)",
"description": "GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...",
"owned_by": "z-ai",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-5.3-flashx",
"name": "GLM 5.3 FlashX",
"description": "GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...",
"owned_by": "z-ai",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-5.3-prime",
"name": "GLM 5.3 Prime",
"description": "GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...",
"owned_by": "z-ai",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-5.3:batch",
"name": "GLM 5.3 (batch)",
"description": "GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...",
"owned_by": "z-ai",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "z-ai/glm-5v-turbo",
"name": "GLM 5V Turbo",
"description": "GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...",
"owned_by": "z-ai",
"context_window": 202752,
"outputs": [
"text"
]
},
{
"id": "zen-embedding",
"owned_by": "zenlm",
"family": "zen",
"context_window": 32768,
"outputs": [
"embeddings"
]
},
{
"id": "zen-embedding-2",
"owned_by": "zenlm",
"family": "zen",
"context_window": 8192,
"outputs": [
"embeddings"
]
},
{
"id": "zen-free",
"owned_by": "zenlm",
"family": "zen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "zen-guard",
"owned_by": "zenlm",
"family": "zen",
"context_window": 128000,
"outputs": [
"text"
]
},
{
"id": "zen-scribe",
"description": "Hanzo's speech-to-text model, which writes down what is said in any language, served at /v1/audio/transcriptions.",
"owned_by": "hanzo",
"family": "zen",
"outputs": [
"transcript"
]
},
{
"id": "zen-vl",
"owned_by": "zenlm",
"family": "zen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "zen-voice-mini",
"description": "Hanzo's text-to-speech voice, served at /v1/audio/speech.",
"owned_by": "hanzo",
"family": "zen",
"outputs": [
"audio"
]
},
{
"id": "zen5",
"owned_by": "zenlm",
"family": "zen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "zen5-coder",
"owned_by": "zenlm",
"family": "zen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "zen5-evo",
"owned_by": "zenlm",
"family": "zen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "zen5-flash",
"owned_by": "zenlm",
"family": "zen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "zen5-mini",
"owned_by": "zenlm",
"family": "zen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "zen5-pro",
"owned_by": "zenlm",
"family": "zen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "zen5-spark",
"owned_by": "zenlm",
"family": "zen",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "zen6",
"owned_by": "zenlm",
"family": "zen",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "zen6-flash",
"owned_by": "zenlm",
"family": "zen",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "~anthropic/claude-fable-latest",
"name": "Claude Fable Latest",
"description": "This model always redirects to the latest model in the Claude Fable family.",
"owned_by": "~anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "~anthropic/claude-haiku-latest",
"name": "Claude Haiku Latest",
"description": "This model always redirects to the latest model in the Claude Haiku family.",
"owned_by": "~anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "~anthropic/claude-opus-latest",
"name": "Claude Opus Latest",
"description": "This model always redirects to the latest model in the Claude Opus family.",
"owned_by": "~anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "~anthropic/claude-sonnet-latest",
"name": "Claude Sonnet Latest",
"description": "This model always redirects to the latest model in the Claude Sonnet family.",
"owned_by": "~anthropic",
"context_window": 1000000,
"outputs": [
"text"
]
},
{
"id": "~deepseek/deepseek-flash-latest",
"name": "DeepSeek Flash Latest",
"description": "This model always redirects to the latest model in the DeepSeek Flash family.",
"owned_by": "~deepseek",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "~deepseek/deepseek-pro-latest",
"name": "DeepSeek Pro Latest",
"description": "This model always redirects to the latest model in the DeepSeek Pro family.",
"owned_by": "~deepseek",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "~deepseek/deepseek-v4-flash-latest",
"name": "DeepSeek V4 Flash Latest",
"description": "This model always redirects to the latest model in the DeepSeek V4 Flash family.",
"owned_by": "~deepseek",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "~google/gemini-flash-latest",
"name": "Gemini Flash Latest",
"description": "This model always redirects to the latest model in the Gemini Flash family.",
"owned_by": "~google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "~google/gemini-pro-latest",
"name": "Gemini Pro Latest",
"description": "This model always redirects to the latest model in the Gemini Pro family.",
"owned_by": "~google",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "~moonshotai/kimi-latest",
"name": "Kimi Latest",
"description": "This model always redirects to the latest model in the Kimi family.",
"owned_by": "~moonshotai",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "~openai/gpt-astra-latest",
"name": "GPT Astra Latest",
"description": "This model always redirects to the latest model in the GPT Astra family.",
"owned_by": "~openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "~openai/gpt-luna-latest",
"name": "GPT Luna Latest",
"description": "This model always redirects to the latest model in the GPT Luna family.",
"owned_by": "~openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "~openai/gpt-mini-latest",
"name": "GPT Mini Latest",
"description": "This model always redirects to the latest model in the GPT Mini family.",
"owned_by": "~openai",
"context_window": 400000,
"outputs": [
"text"
]
},
{
"id": "~openai/gpt-sol-latest",
"name": "GPT Sol Latest",
"description": "This model always redirects to the latest model in the GPT Sol family.",
"owned_by": "~openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "~openai/gpt-terra-latest",
"name": "GPT Terra Latest",
"description": "This model always redirects to the latest model in the GPT Terra family.",
"owned_by": "~openai",
"context_window": 1050000,
"outputs": [
"text"
]
},
{
"id": "~typesafe/jev-latest",
"name": "Jev",
"owned_by": "typesafe",
"outputs": [
"decision"
]
},
{
"id": "~unbiased/pareto-latest",
"name": "Pareto Latest",
"description": "This model always redirects to the latest model in the Pareto family.",
"owned_by": "~unbiased",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "~x-ai/grok-latest",
"name": "Grok Latest",
"description": "This model always redirects to the latest Grok model from xAI.",
"owned_by": "~x-ai",
"context_window": 500000,
"outputs": [
"text"
]
},
{
"id": "~z-ai/glm-flash-latest",
"name": "GLM Flash Latest",
"description": "This model always redirects to the latest model in the GLM Flash family.",
"owned_by": "~z-ai",
"context_window": 1048576,
"outputs": [
"text"
]
},
{
"id": "~z-ai/glm-latest",
"name": "GLM Latest",
"description": "This model always redirects to the latest GLM model from Z.ai.",
"owned_by": "~z-ai",
"context_window": 1048576,
"outputs": [
"text"
]
}
],
"own": [
{
"name": "zen-embedding",
"fullName": "Zen Embedding",
"description": "Dense text embeddings for semantic search, retrieval, and clustering.",
"features": [
"8K context",
"Embeddings"
],
"tier": "starter",
"context": 8192,
"links": {
"github": "https://github.com/zenlm/zen-embedding",
"huggingface": "https://huggingface.co/zenlm/zen-embedding"
}
},
{
"name": "zen-guard",
"fullName": "Zen Guard — Content Safety",
"description": "Safety classifier for moderation and guardrails across a broad category and language set.",
"features": [
"128K context",
"Safety classifier"
],
"tier": "starter",
"context": 128000,
"links": {
"github": "https://github.com/zenlm/zen-guard",
"huggingface": "https://huggingface.co/zenlm/zen-guard"
}
},
{
"name": "zen-vl",
"fullName": "Zen VL — Vision-Language",
"description": "Reads images and reasons over them — visual Q&A, document and chart understanding, grounded captioning.",
"features": [
"128K context",
"Vision + Language"
],
"tier": "pro",
"context": 128000,
"links": {
"github": "https://github.com/zenlm/zen-vl"
}
},
{
"name": "zen5",
"fullName": "Zen5 (Default)",
"description": "Canonical Zen5 default. a 35B frontier MoE (3B active) (35B total / 3B active per token, released Apr 2026, Apache-2.0). 256K context, agentic-trained, OpenAI + Anthropic API. The everyday Zen5 chat model.",
"features": [
"256K context window",
"35B total / 3B active (MoE)",
"Zen base",
"Apr 2026 release",
"OpenAI + Anthropic API"
],
"tier": "pro",
"context": 1000000,
"specs": {
"arch": "Zen frontier MoE",
"params": "35B (3B active)"
},
"links": {
"github": "https://github.com/zenlm/zen5"
}
},
{
"name": "zen5-coder",
"fullName": "Zen5 Coder",
"description": "Code-specialized Zen5 tier. 80B sparse MoE tuned for repo-scale code understanding, agentic refactoring, and tool-use coding loops.",
"features": [
"256K context",
"80B sparse MoE",
"Code-specialized",
"Agentic / tool-use"
],
"tier": "pro",
"context": 1000000,
"specs": {
"arch": "Zen Coder MoE",
"params": "80B (MoE)"
}
},
{
"name": "zen5-flash",
"fullName": "Zen5 Flash",
"description": "Smallest and cheapest text-only Zen5 chat tier. 4B-class dense, sub-100ms TTFT, 32K context. For high-volume routing and simple agent loops.",
"features": [
"32K context window",
"4B parameters (dense)",
"Sub-100ms TTFT",
"Highest throughput"
],
"tier": "starter",
"context": 65536,
"specs": {
"arch": "Zen dense",
"params": "4B"
}
},
{
"name": "zen5-mini",
"fullName": "Zen5 Mini",
"description": "Frontier agentic at the lowest cost in the family. Built on a 230B agentic MoE (10B active) (230B MoE / 10B active, released Feb 2026). 80.2% SWE-Bench Verified, 76.3% BrowseComp; trained on 200K+ real-world environments via large-scale RL.",
"features": [
"192K context window",
"230B total / 10B active (MoE)",
"Zen agentic base",
"Frontier agentic / coding",
"Lowest $/token in family"
],
"tier": "pro",
"context": 32768,
"specs": {
"arch": "Zen MoE",
"params": "230B (10B active)"
}
},
{
"name": "zen5-pro",
"fullName": "Zen5 Pro",
"description": "Zen Flash IQ2_XXS-imatrix weights (81 GB GGUF on zenlm/zen-5-pro-gguf). 284B total / 37B active per token, 1M context, asymmetric routed-MoE quant. Fits a single 128 GB Apple Silicon / DGX Spark / H100 80 GB.",
"features": [
"1M context window",
"284B total / 37B active (MoE)",
"Zen Flash base",
"IQ2_XXS-imatrix quant (81 GB)",
"Runs on 128 GB hardware"
],
"tier": "ultra",
"context": 1000000,
"specs": {
"arch": "Zen Flash MoE",
"params": "284B (37B active)"
}
},
{
"name": "enso",
"fullName": "Enso",
"description": "Hanzo's proprietary frontier model — Opus-class reasoning by default with 1M-context overflow.",
"features": [
"1M context window",
"Frontier reasoning"
],
"tier": "ultra max",
"context": 1000000,
"links": {
"github": "https://github.com/hanzoai/enso"
}
},
{
"name": "enso-flash",
"fullName": "Enso Flash",
"description": "Fast, economical Enso tier for high-volume, low-latency everyday work, with 1M-context overflow.",
"features": [
"1M context window",
"Low latency"
],
"tier": "pro",
"context": 262144,
"links": {
"github": "https://github.com/hanzoai/enso"
}
},
{
"name": "enso-ultra",
"fullName": "Enso Ultra",
"description": "Adaptive fan-out — probes a task-appropriate model, escalates to a top-K panel only when needed, then verifies-then-selects the best answer.",
"features": [
"200K context window",
"Adaptive fan-out"
],
"tier": "ultra max",
"context": 1000000,
"links": {
"github": "https://github.com/hanzoai/enso"
}
},
{
"name": "kai",
"fullName": "Kai",
"description": "Hanzo's decision model: a typed answer with a probability on every option, at POST /v1/decisions. A native decision writes 0 output tokens.",
"features": [
"choice, score and noul questions",
"A probability on every option",
"0 output tokens"
],
"tier": "starter",
"specs": {
"arch": "Encoder (mmBERT-base, 22 layers × 768)",
"params": "322.1M encoder, 60.2M yes/no reader"
},
"links": {
"github": "https://github.com/hanzoai/kai"
}
},
{
"name": "hanzo/kai",
"fullName": "Kai",
"description": "Hanzo's decision model: a typed answer with a probability on every option, at POST /v1/decisions. A native decision writes 0 output tokens.",
"features": [
"choice, score and noul questions",
"A probability on every option",
"0 output tokens"
],
"tier": "starter",
"specs": {
"arch": "Encoder (mmBERT-base, 22 layers × 768)",
"params": "322.1M encoder, 60.2M yes/no reader"
},
"links": {
"github": "https://github.com/hanzoai/kai"
}
},
{
"name": "typesafe/jev-1.13",
"fullName": "Jev 1.13",
"description": "TypeSafe's decision model, reached through OpenRouter, at its list price: $0.042 per million input tokens. Output is free.",
"features": [
"Decisions"
],
"tier": "starter",
"specs": {
"arch": "decision"
}
},
{
"name": "~typesafe/jev-latest",
"fullName": "Jev",
"description": "TypeSafe's decision model, reached through OpenRouter, at its list price: $0.042 per million input tokens. Output is free.",
"features": [
"Decisions"
],
"tier": "starter",
"specs": {
"arch": "decision"
}
},
{
"name": "zenlm/zen6",
"fullName": "Zen 6",
"description": "Zen 6 answering typed decisions at /v1/decisions under a strict JSON schema. $2.28 per million input tokens and $7.26 per million output tokens.",
"features": [
"Decisions"
],
"tier": "starter",
"specs": {
"arch": "decision"
}
},
{
"name": "zenlm/zen6-flash",
"fullName": "Zen 6 Flash",
"description": "Zen 6 Flash answering typed decisions at /v1/decisions under a strict JSON schema. $2.28 per million input tokens and $7.26 per million output tokens.",
"features": [
"Decisions"
],
"tier": "starter",
"specs": {
"arch": "decision"
}
},
{
"name": "enso-pro",
"fullName": "enso-pro"
}
]
}
Reference in New Issue View Git Blame Copy Permalink