Files

2 lines
20 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.
{"source":"https://commerce.hanzo.ai/v1/models?id=anthropic/claude-fable-5.1,anthropic/claude-opus-5,anthropic/claude-sonnet-5.5,enso-auto,enso-flash,enso-max,enso-pro,enso-ultra,kai,openai/gpt-5.5,openai/gpt-6-astra,zen6,zen6-coder,zen6-flash,zen6-max,zen-embedding,zen-embedding-3 and https://commerce.hanzo.ai/v1/pricing/models?id=anthropic/claude-fable-5,anthropic/claude-fable-5.1,anthropic/claude-haiku-5.5,anthropic/claude-opus-4.8,anthropic/claude-opus-5.5,anthropic/claude-sonnet-5,anthropic/claude-sonnet-5.5,deepseek/deepseek-v4-pro,openai/gpt-4o,openai/gpt-5.5,openai/gpt-5.6-sol,openai/gpt-6-sol,moonshotai/kimi-k3,x-ai/grok-4.7,z-ai/glm-5.3,enso-auto,enso-flash,enso-pro,enso-max,enso-ultra,kai,zen6-flash,zen6,zen6-coder,zen6-max,zen-embedding,zen-embedding-3,zen5,zen5-coder,zen5-mini,zen5-pro,zen-vl,zen-guard","fetched_at":"2026-11-11T00:58:33.098Z","models":[{"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...","family":"","context_window":1000000,"endpoint":"/v1/chat/completions","pricing":{"prompt":"0.00001113025","completion":"0.00005565125","input_per_million":11.13025,"output_per_million":55.65125,"rates":{"completion":"0.00005565125","input_cache_read":"0.00000027825625","input_cache_write":"0.0000139128125","input_cache_write_1h":"0.0000222605","prompt":"0.00001113025","web_search":"0.01113025"}}},{"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...","family":"","context_window":1000000,"endpoint":"/v1/chat/completions","pricing":{"prompt":"0.000005565125","completion":"0.000027825625","input_per_million":5.565125,"output_per_million":27.825625,"rates":{"completion":"0.000027825625","input_cache_read":"0.0000005565125","input_cache_write":"0.00000695640625","input_cache_write_1h":"0.00001113025","prompt":"0.000005565125","web_search":"0.01113025"}}},{"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...","family":"","context_window":1000000,"endpoint":"/v1/chat/completions","pricing":{"prompt":"0.00000222605","completion":"0.00001113025","input_per_million":2.22605,"output_per_million":11.13025,"rates":{"completion":"0.00001113025","input_cache_read":"0.0000001113025","input_cache_write":"0.0000027825625","input_cache_write_1h":"0.0000044521","prompt":"0.00000222605","web_search":"0.01113025"}}},{"id":"enso-auto","name":"Enso","description":"Routes each request to one tier: enso-flash at instant, off, none, minimal, default, low; enso-pro at medium; enso-max at high; enso-ultra at xhigh, max. With no effort, or auto, the router chooses, starting at enso-flash and going deeper only when it or Kai judges the request needs it. It bills at the price of the tier that answers; the price shown is the router's start. When nothing pays for a tier it answers on that tier's no-cost rungs, at no charge, and says so.","family":"enso","context_window":1000000,"endpoint":"/v1/chat/completions","pricing":{"prompt":"0.00000033","completion":"0.00000165","input_per_million":0.33,"output_per_million":1.65,"rates":{"input_cache_read":"0.000000033","input_cache_write":"0.0000004125"}}},{"id":"enso-flash","description":"","family":"enso","context_window":1000000,"endpoint":"/v1/chat/completions","pricing":{"prompt":"0.00000033","completion":"0.00000165","input_per_million":0.33,"output_per_million":1.65,"rates":{"input_cache_read":"0.000000033","input_cache_write":"0.0000004125"}}},{"id":"enso-max","description":"","family":"enso","context_window":1000000,"endpoint":"/v1/chat/completions","pricing":{"prompt":"0.0000043","completion":"0.0000215","input_per_million":4.3,"output_per_million":21.5,"rates":{"input_cache_read":"0.000000215","input_cache_write":"0.000005375"}}},{"id":"enso-pro","description":"","family":"enso","context_window":1000000,"endpoint":"/v1/chat/completions","pricing":{"prompt":"0.0000033","completion":"0.0000165","input_per_million":3.3,"output_per_million":16.5,"rates":{"input_cache_read":"0.000000165","input_cache_write":"0.000004125"}}},{"id":"enso-ultra","description":"","family":"enso","context_window":1000000,"endpoint":"/v1/chat/completions","pricing":{"prompt":"0.000005236","completion":"0.00002618","input_per_million":5.236,"output_per_million":26.18,"rates":{"input_cache_read":"0.0000002618","input_cache_write":"0.000006545"}}},{"id":"kai","name":"Kai 1.7","description":"Hanzo's decision model, which answers typed questions at /v1/decisions rather than a chat turn.","family":"kai","context_window":null,"endpoint":"/v1/decisions","pricing":{"prompt":"0.000000021","completion":"0","input_per_million":0.021,"output_per_million":0,"rates":{"input_cache_read":"0.0000000021","input_cache_write":"0.00000002625"}}},{"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...","family":"","context_window":1050000,"endpoint":"/v1/chat/completions","pricing":{"prompt":"0.000005565125","completion":"0.00003339075","input_per_million":5.565125,"output_per_million":33.39075,"rates":{"completion":"0.00003339075","input_cache_read":"0.0000005565125","input_cache_write":"0.00000695640625","prompt":"0.000005565125","web_search":"0.01113025"},"overrides":[{"completion":"0.000050086125","input_cache_read":"0.000001113025","min_prompt_tokens":272000,"prompt":"0.00001113025"}]}},{"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...","family":"","context_window":1050000,"endpoint":"/v1/chat/completions","pricing":{"prompt":"0.00001113025","completion":"0.00005565125","input_per_million":11.13025,"output_per_million":55.65125,"rates":{"completion":"0.00005565125","input_cache_read":"0.000001113025","input_cache_write":"0.0000139128125","prompt":"0.00001113025","web_search":"0.01113025"},"overrides":[{"completion":"0.000083476875","input_cache_read":"0.00000222605","input_cache_write":"0.000027825625","min_prompt_tokens":272000,"prompt":"0.0000222605"}]}},{"id":"zen-embedding","description":"","family":"zen","context_window":32768,"endpoint":"/v1/embeddings","pricing":{"prompt":"0.00000001","completion":"0.00000001","input_per_million":0.01,"output_per_million":0.01,"rates":{"input_cache_read":"0.00000001","input_cache_write":"0.0000000125"}}},{"id":"zen-embedding-3","description":"","family":"zen","context_window":32768,"endpoint":"/v1/embeddings","pricing":{"prompt":"0.00000017","completion":"0.00000017","input_per_million":0.17,"output_per_million":0.17,"rates":{"input_cache_read":"0.00000017","input_cache_write":"0.0000002125"}}},{"id":"zen6","description":"","family":"zen","context_window":1048576,"endpoint":"/v1/chat/completions","pricing":{"prompt":"0.0000006","completion":"0.0000024","input_per_million":0.6,"output_per_million":2.4,"rates":{"input_cache_read":"0.000000024","input_cache_write":"0.00000075"}}},{"id":"zen6-coder","description":"","family":"zen","context_window":1048576,"endpoint":"/v1/chat/completions","pricing":{"prompt":"0.00000165","completion":"0.000013","input_per_million":1.65,"output_per_million":13,"rates":{"input_cache_read":"0.000000165","input_cache_write":"0.0000020625"}}},{"id":"zen6-flash","description":"","family":"zen","context_window":1048576,"endpoint":"/v1/chat/completions","pricing":{"prompt":"0.00000015","completion":"0.0000006","input_per_million":0.15,"output_per_million":0.6,"rates":{"input_cache_read":"0.000000008","input_cache_write":"0.0000001875"}}},{"id":"zen6-max","description":"","family":"zen","context_window":1048576,"endpoint":"/v1/chat/completions","pricing":{"prompt":"0.000028","completion":"0.000168","input_per_million":28,"output_per_million":168,"rates":{"input_cache_read":"0.0000028","input_cache_write":"0.000035"}}}],"catalog":[{"id":"zen-embedding","fullName":"Zen Embedding","description":"Dense text embeddings for semantic search, retrieval, and clustering.","family":"zen","order":null,"context":8192,"endpoint":null,"features":["8K context","Embeddings"],"specs":null,"pricing":{"cacheRead":0.01,"cacheWrite":0.0125,"input":0.01,"output":0.01}},{"id":"zen-guard","fullName":"Zen Guard — Content Safety","description":"Safety classifier for moderation and guardrails across a broad category and language set.","family":"zen","order":null,"context":128000,"endpoint":null,"features":["128K context","Safety classifier"],"specs":null,"pricing":{"cacheRead":0.03,"cacheWrite":0.375,"input":0.3,"output":0.96}},{"id":"zen-vl","fullName":"Zen VL — Vision-Language","description":"Reads images and reasons over them — visual Q&A, document and chart understanding, grounded captioning.","family":"zen","order":null,"context":128000,"endpoint":null,"features":["128K context","Vision + Language"],"specs":null,"pricing":{"cacheRead":null,"cacheWrite":null,"input":0,"output":0}},{"id":"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.","family":"zen","order":null,"context":1000000,"endpoint":null,"features":["256K context window","35B total / 3B active (MoE)","Zen base","Apr 2026 release","OpenAI + Anthropic API"],"specs":{"arch":"Zen frontier MoE","params":"35B (3B active)"},"pricing":{"cacheRead":null,"cacheWrite":null,"input":0,"output":0}},{"id":"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.","family":"zen","order":null,"context":1000000,"endpoint":null,"features":["256K context","80B sparse MoE","Code-specialized","Agentic / tool-use"],"specs":{"arch":"Zen Coder MoE","params":"80B (MoE)"},"pricing":{"cacheRead":null,"cacheWrite":null,"input":0,"output":0}},{"id":"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.","family":"zen","order":null,"context":32768,"endpoint":null,"features":["192K context window","230B total / 10B active (MoE)","Zen agentic base","Frontier agentic / coding","Lowest $/token in family"],"specs":{"arch":"Zen MoE","params":"230B (10B active)"},"pricing":{"cacheRead":null,"cacheWrite":null,"input":0,"output":0}},{"id":"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.","family":"zen","order":null,"context":1000000,"endpoint":null,"features":["1M context window","284B total / 37B active (MoE)","Zen Flash base","IQ2_XXS-imatrix quant (81 GB)","Runs on 128 GB hardware"],"specs":{"arch":"Zen Flash MoE","params":"284B (37B active)"},"pricing":{"cacheRead":null,"cacheWrite":null,"input":0,"output":0}},{"id":"enso-auto","fullName":"Enso Auto","description":"Adaptive Enso router — routes each request to Enso Flash, Pro, Max, or Ultra by reasoning depth and bills at the tier that answers, starting at Enso Flash.","family":"enso","order":1,"context":1000000,"endpoint":null,"features":["1M context window","Frontier reasoning"],"specs":null,"pricing":{"cacheRead":0.033,"cacheWrite":0.4125,"input":0.33,"output":1.65}},{"id":"enso-flash","fullName":"Enso Flash","description":"Fast, economical Enso model for high-volume, low-latency everyday chat, coding, and tool calls.","family":"enso","order":2,"context":1000000,"endpoint":null,"features":["1M context window","Low latency"],"specs":null,"pricing":{"cacheRead":0.033,"cacheWrite":0.4125,"input":0.33,"output":1.65}},{"id":"enso-ultra","fullName":"Enso Ultra","description":"Adaptive fan-out frontier model — probes a task-appropriate model, escalates to a top-K panel when needed, then verifies and selects the best answer.","family":"enso","order":5,"context":1000000,"endpoint":null,"features":["200K context window","Adaptive fan-out"],"specs":null,"pricing":{"cacheRead":0.2618,"cacheWrite":6.545,"input":5.236,"output":26.18}},{"id":"kai","fullName":"Kai","description":"Hanzo Kai — typed decision and structured judgment model answering at /v1/decisions under strict JSON schema.","family":"kai","order":null,"context":131072,"endpoint":"/v1/decisions","features":["choice, score and noul questions","A probability on every option","0 output tokens"],"specs":{"arch":"Encoder (mmBERT-base, 22 layers × 768)","params":"322.1M encoder, 60.2M yes/no reader"},"pricing":{"cacheRead":0.0021,"cacheWrite":0.02625,"input":0.021,"output":0}},{"id":"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.","family":"","order":null,"context":null,"endpoint":"/v1/decisions","features":["Decisions"],"specs":{"arch":"decision"},"pricing":{"cacheRead":0.22799999999999998,"cacheWrite":2.8499999999999996,"input":2.28,"output":7.26}},{"id":"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.","family":"","order":null,"context":null,"endpoint":"/v1/decisions","features":["Decisions"],"specs":{"arch":"decision"},"pricing":{"cacheRead":0.22799999999999998,"cacheWrite":2.8499999999999996,"input":2.28,"output":7.26}},{"id":"enso-max","fullName":"Enso Max","description":"Extended frontier reasoning model for deep multi-step architecture, research, and autonomous coding loops.","family":"enso","order":4,"context":1000000,"endpoint":null,"features":[],"specs":null,"pricing":{"cacheRead":0.215,"cacheWrite":5.375,"input":4.3,"output":21.5}},{"id":"enso-pro","fullName":"Enso Pro","description":"Balanced frontier reasoning and coding model for production agents, tool use, and repo-scale engineering.","family":"enso","order":3,"context":1000000,"endpoint":null,"features":[],"specs":null,"pricing":{"cacheRead":0.165,"cacheWrite":4.125,"input":3.3,"output":16.5}},{"id":"anthropic/claude-opus-5.5","fullName":"Anthropic: Claude Opus 5.5","description":"","family":"","order":null,"context":null,"endpoint":null,"features":["1M context window","text+image+file->text"],"specs":null,"pricing":{"cacheRead":0.2,"cacheWrite":5,"input":4,"output":20}},{"id":"anthropic/claude-sonnet-5.5","fullName":"Anthropic: Claude Sonnet 5.5","description":"","family":"","order":null,"context":null,"endpoint":null,"features":["1M context window","text+image+file->text"],"specs":null,"pricing":{"cacheRead":0.1,"cacheWrite":2.5,"input":2,"output":10}},{"id":"anthropic/claude-haiku-5.5","fullName":"Anthropic: Claude Haiku 5.5","description":"","family":"","order":null,"context":null,"endpoint":null,"features":["1M context window","text+image+file->text"],"specs":null,"pricing":{"cacheRead":0.01,"cacheWrite":0.125,"input":0.1,"output":0.5}},{"id":"openai/gpt-5.6-sol","fullName":"OpenAI: GPT-5.6 Sol","description":"","family":"","order":null,"context":null,"endpoint":null,"features":["1M context window","text+image+file->text"],"specs":null,"pricing":{"cacheRead":0.4,"cacheWrite":5,"input":4,"output":20}},{"id":"x-ai/grok-4.7","fullName":"SpaceXAI: Grok 4.7","description":"","family":"","order":null,"context":null,"endpoint":null,"features":["500k context window","text+image+file->text"],"specs":null,"pricing":{"cacheRead":0.5,"cacheWrite":null,"input":2,"output":6}},{"id":"deepseek/deepseek-v4-pro","fullName":"DeepSeek: DeepSeek V4 Pro 0423","description":"","family":"","order":null,"context":null,"endpoint":null,"features":["1M context window","text->text"],"specs":null,"pricing":{"cacheRead":0.08,"cacheWrite":null,"input":0.955,"output":1.91}},{"id":"moonshotai/kimi-k3","fullName":"MoonshotAI: Kimi K3","description":"","family":"","order":null,"context":null,"endpoint":null,"features":["1M context window","text+image+video->text"],"specs":null,"pricing":{"cacheRead":0.182,"cacheWrite":null,"input":0.192,"output":16}},{"id":"anthropic/claude-fable-5","fullName":"Anthropic: Claude Fable 5","description":"","family":"","order":null,"context":null,"endpoint":null,"features":["1M context window","text+image+file->text"],"specs":null,"pricing":{"cacheRead":1,"cacheWrite":12.5,"input":10,"output":50}},{"id":"anthropic/claude-opus-4.8","fullName":"Anthropic: Claude Opus 4.8","description":"","family":"","order":null,"context":null,"endpoint":null,"features":["1M context window","text+image+file->text"],"specs":null,"pricing":{"cacheRead":0.5,"cacheWrite":6.25,"input":5,"output":25}},{"id":"anthropic/claude-sonnet-5","fullName":"Anthropic: Claude Sonnet 5","description":"","family":"","order":null,"context":null,"endpoint":null,"features":["1M context window","text+image+file->text"],"specs":null,"pricing":{"cacheRead":0.2,"cacheWrite":2.5,"input":2,"output":10}},{"id":"openai/gpt-4o","fullName":"OpenAI: GPT-4o","description":"","family":"","order":null,"context":null,"endpoint":null,"features":["128k context window","text+image+file->text"],"specs":null,"pricing":{"cacheRead":1.25,"cacheWrite":null,"input":2.5,"output":10}},{"id":"openai/gpt-5.5","fullName":"OpenAI: GPT-5.5","description":"","family":"","order":null,"context":null,"endpoint":null,"features":["1M context window","text+image+file->text"],"specs":null,"pricing":{"cacheRead":0.5,"cacheWrite":null,"input":5,"output":30}},{"id":"openai/gpt-6-sol","fullName":"OpenAI: GPT-6 Sol","description":"","family":"","order":null,"context":null,"endpoint":null,"features":["1M context window","text+image+file->text"],"specs":null,"pricing":{"cacheRead":0.2,"cacheWrite":2.5,"input":2,"output":10}},{"id":"anthropic/claude-fable-5.1","fullName":"Anthropic: Claude Fable 5.1","description":"","family":"","order":null,"context":null,"endpoint":null,"features":["1M context window","text+image+file->text"],"specs":null,"pricing":{"cacheRead":0.25,"cacheWrite":12.5,"input":10,"output":50}},{"id":"z-ai/glm-5.3","fullName":"Z.ai: GLM 5.3","description":"","family":"","order":null,"context":null,"endpoint":null,"features":["1M context window","text->text"],"specs":null,"pricing":{"cacheRead":0.069,"cacheWrite":null,"input":0.07,"output":1.4}}],"names":{"zen-embedding":"Zen Embedding","zen-guard":"Zen Guard — Content Safety","zen-vl":"Zen VL — Vision-Language","zen5":"Zen5 (Default)","zen5-coder":"Zen5 Coder","zen5-mini":"Zen5 Mini","zen5-pro":"Zen5 Pro","enso-auto":"Enso Auto","enso-flash":"Enso Flash","enso-ultra":"Enso Ultra","kai":"Kai","zenlm/zen6":"Zen 6","zenlm/zen6-flash":"Zen 6 Flash","enso-max":"Enso Max","enso-pro":"Enso Pro","anthropic/claude-opus-5.5":"Anthropic: Claude Opus 5.5","anthropic/claude-sonnet-5.5":"Anthropic: Claude Sonnet 5.5","anthropic/claude-haiku-5.5":"Anthropic: Claude Haiku 5.5","openai/gpt-5.6-sol":"OpenAI: GPT-5.6 Sol","x-ai/grok-4.7":"SpaceXAI: Grok 4.7","deepseek/deepseek-v4-pro":"DeepSeek: DeepSeek V4 Pro 0423","moonshotai/kimi-k3":"MoonshotAI: Kimi K3","anthropic/claude-fable-5":"Anthropic: Claude Fable 5","anthropic/claude-opus-4.8":"Anthropic: Claude Opus 4.8","anthropic/claude-sonnet-5":"Anthropic: Claude Sonnet 5","openai/gpt-4o":"OpenAI: GPT-4o","openai/gpt-5.5":"OpenAI: GPT-5.5","openai/gpt-6-sol":"OpenAI: GPT-6 Sol","anthropic/claude-fable-5.1":"Anthropic: Claude Fable 5.1","z-ai/glm-5.3":"Z.ai: GLM 5.3"}}