mirror of
https://github.com/hanzo-docs/docs.git
synced 2026-10-28 07:09:50 +00:00
zeekay
42f167196d
Replace hardcoded model prices across all docs surfaces with client-side fetches from pricing.hanzo.ai/v1/pricing. Static fallback values remain in zen-models for SSR/build time. Changes: - zen-models: fix 10 wrong static prices, add fetchPricing() API - zen-docs: new DynamicModelTable component for MDX pages - zen-docs: pricing.mdx, models.mdx, api/models.mdx, index.mdx all use dynamic tables instead of hardcoded price columns - platform: extract DynamicAiModels component, remove static array - bot-docs: extract DynamicTokenPricing, fetch live per-1K rates
67 lines
1.7 KiB
Plaintext
67 lines
1.7 KiB
Plaintext
---
|
|
title: Models
|
|
description: All Zen models -- capabilities, pricing, and recommended use cases
|
|
---
|
|
|
|
# Available Models
|
|
|
|
## List Models
|
|
|
|
```
|
|
GET https://api.hanzo.ai/v1/models
|
|
```
|
|
|
|
Returns all available Zen models.
|
|
|
|
## Zen4 Generation (9 models)
|
|
|
|
The latest generation. Flagship, reasoning, and code models.
|
|
|
|
<DynamicModelTable generation="zen4" showArch showContext />
|
|
|
|
## Zen3 Generation (5 models)
|
|
|
|
Multimodal, vision, safety, and embedding models.
|
|
|
|
<DynamicModelTable generation="zen3" showArch showContext />
|
|
|
|
## Model Selection Guide
|
|
|
|
### By Task
|
|
|
|
| Task | Recommended Model |
|
|
|------|-------------------|
|
|
| General chat | zen4 |
|
|
| Maximum reasoning | zen4-ultra |
|
|
| Deep reasoning (CoT) | zen4-thinking |
|
|
| Code generation | zen4-coder |
|
|
| Fast code iteration | zen4-coder-flash |
|
|
| Premium code accuracy | zen4-coder-pro |
|
|
| Image understanding | zen3-vl |
|
|
| Multimodal (text+vision+audio) | zen3-omni |
|
|
| Content moderation | zen3-guard |
|
|
| Text embeddings | zen3-embedding |
|
|
| Edge / mobile | zen3-nano |
|
|
| Budget-friendly | zen4-mini |
|
|
| Extended context docs | zen4-max |
|
|
| High capability | zen4-pro |
|
|
|
|
### By Budget
|
|
|
|
| Budget | Recommended |
|
|
|--------|-------------|
|
|
| Free tier ($5) | zen4-mini, zen3-nano |
|
|
| Low cost | zen4-mini, zen3-vl, zen4-coder-flash |
|
|
| Standard | zen4-pro, zen4-coder, zen4-thinking |
|
|
| Premium | zen4, zen4-ultra, zen4-coder-pro |
|
|
|
|
## Open Weights
|
|
|
|
All Zen models are also available as open weights for self-hosting:
|
|
|
|
- **HuggingFace**: [huggingface.co/zenlm](https://huggingface.co/zenlm)
|
|
- **Ollama**: `ollama run zen4`
|
|
- **Formats**: SafeTensors, GGUF, MLX
|
|
|
|
Cloud API via Hanzo gives you managed infrastructure, usage tracking, and pay-per-token billing without running your own GPUs.
|