Directory
Models, open and hosted
Context windows, prices, licences, quantizations and hardware needs for 2,153 models. Every fact names its source and the day it was read, and a fact no source states says Unknown.
Browse the models
The list shows the models that the most providers serve first, newer models first among equals, then the models no provider lists, most downloaded on Hugging Face first. You can order it by date, downloads or name instead. Payment never changes the order or which models are listed.
Showing the first 40 of 2,153 models.
- Kimi K2.6MoonshotAI
- Parameters
- 1.0T
- Context
- 262,144
- Licence
- other
- Input, per million tokens
- 0.300 USD
- gpt-oss-120bOpenAI
- Parameters
- 116.8B
- Context
- 131,072
- Licence
- apache-2.0
- Input, per million tokens
- 0.030 USD
- Kimi K3MoonshotAI
- Parameters
- 2.8T
- Context
- 1,048,576
- Licence
- other
- Input, per million tokens
- 1.35 USD
- GLM 5.3 FlashZ.ai
- Parameters
- 321.3B
- Context
- 1,310,720
- Licence
- mit
- Input, per million tokens
- 0.045 USD
- GLM 5.2Z.ai
- Parameters
- 753.3B
- Context
- 1,048,576
- Licence
- mit
- Input, per million tokens
- 0.561 USD
- GLM 5.3Z.ai
- Parameters
- 753.3B
- Context
- 1,310,720
- Licence
- other
- Input, per million tokens
- 0.561 USD
- DeepSeek V4 Flash 0731DeepSeek
- Parameters
- 304.2B
- Context
- 1,310,720
- Licence
- mit
- Input, per million tokens
- 0.030 USD
- Kimi K2.7 CodeMoonshotAI
- Parameters
- 1.0T
- Context
- 262,144
- Licence
- other
- Input, per million tokens
- 0.656 USD
- Qwen3.8 27BQwen
- Parameters
- 27.8B
- Context
- 1,000,000
- Licence
- apache-2.0
- Input, per million tokens
- 0.094 USD
- DeepSeek V4.1 FlashDeepSeek
- Parameters
- 763.2B
- Context
- 1,048,576
- Licence
- mit
- Input, per million tokens
- 0.040 USD
- Gemma 4 31BGoogle
- Parameters
- 31.3B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.090 USD
- DeepSeek V4 Pro 0813DeepSeek
- Parameters
- 1.7T
- Context
- 1,048,576
- Licence
- mit
- Input, per million tokens
- 0.389 USD
- Qwen3.5 397B A17BQwen
- Parameters
- 403.4B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.172 USD
- gpt-oss-20bOpenAI
- Parameters
- 20.9B
- Context
- 131,072
- Licence
- apache-2.0
- Input, per million tokens
- 0.018 USD
- DeepSeek V4 Pro 0423DeepSeek
- Parameters
- 1.6T
- Context
- 1,048,576
- Licence
- mit
- Input, per million tokens
- 0.435 USD
- DeepSeek V4 Flash 0423DeepSeek
- Parameters
- 290.9B
- Context
- 1,048,576
- Licence
- mit
- Input, per million tokens
- 0.078 USD
- Gemma 4 26B A4BGoogle
- Parameters
- 25.8B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.042 USD
- GLM 5.1Z.ai
- Parameters
- 753.9B
- Context
- 204,800
- Licence
- mit
- Input, per million tokens
- 0.615 USD
- Qwen3 235B A22B Instruct 2507Qwen
- Parameters
- 235.1B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.087 USD
- Llama 3.3 70B InstructMeta
- Parameters
- 70.6B
- Context
- 131,072
- Licence
- llama3.3
- Input, per million tokens
- 0.050 USD
- Kimi K2.5MoonshotAI
- Parameters
- 1.0T
- Context
- 262,144
- Licence
- other
- Input, per million tokens
- 0.300 USD
- Qwen3.6 27BQwen
- Parameters
- 27.8B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.203 USD
- Qwen3.6 35B A3BQwen
- Parameters
- 36.0B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.050 USD
- Qwen3.5-35B-A3BQwen
- Parameters
- 36.0B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.057 USD
- DeepSeek V3.2DeepSeek
- Parameters
- 685.4B
- Context
- 163,840
- Licence
- mit
- Input, per million tokens
- 0.209 USD
- Qwen3.5-122B-A10BQwen
- Parameters
- 125.1B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.115 USD
- Qwen3.5-27BQwen
- Parameters
- 27.8B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.086 USD
- Hy3Tencent
- Parameters
- 298.8B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.066 USD
- Qwen3.5-9BQwen
- Parameters
- 9.7B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.050 USD
- GLM 5Z.ai
- Parameters
- 753.9B
- Context
- 204,800
- Licence
- mit
- Input, per million tokens
- 0.600 USD
- Qwen3 Next 80B A3B InstructQwen
- Parameters
- 81.3B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.090 USD
- DeepSeek V3.1DeepSeek
- Parameters
- 684.5B
- Context
- 163,840
- Licence
- mit
- Input, per million tokens
- 0.200 USD
- Qwen3.8 2.4T A95BQwen
- Parameters
- 2.4T
- Context
- 1,048,576
- Licence
- other
- Input, per million tokens
- 1.95 USD
- InklingThinking Machines
- Parameters
- 952.4B
- Context
- 1,048,576
- Licence
- apache-2.0
- Input, per million tokens
- 0.950 USD
- MiniMax M2.7MiniMax
- Parameters
- 228.7B
- Context
- 204,800
- Licence
- other
- Input, per million tokens
- 0.210 USD
- MiniMax M2.5MiniMax
- Parameters
- 228.7B
- Context
- 204,800
- Licence
- other
- Input, per million tokens
- 0.150 USD
- Qwen3 Coder 480B A35BQwen
- Parameters
- 480.2B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.220 USD
- Qwen3 Coder NextQwen
- Parameters
- 79.7B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.120 USD
- GLM 4.7Z.ai
- Parameters
- 358.3B
- Context
- 204,800
- Licence
- mit
- Input, per million tokens
- 0.200 USD
- Qwen3 VL 235B A22B InstructQwen
- Parameters
- 235.7B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.200 USD
Sources and dates
Every row keeps the address of each source it uses and the day it was read. A fact no source states is shown as Unknown. The directory was built on .
| Source | What it gives | Terms | Rows | Last read |
|---|---|---|---|---|
| OpenRouter Models API | Context length, output limit, supported parameters and benchmark indexes of hosted models. OpenRouter's documentation says its Models API makes this information freely available; the build reads only that documented interface. | Terms | 341 | 2026-09-24 |
| OpenRouter model endpoints API | The providers that serve each model through OpenRouter, with the prices OpenRouter lists for each route. | Terms | 341 | 2026-09-24 |
| Hugging Face Hub API | Licence, parameter count, publication date, downloads and task of open models, read within the API's published request limit. | Terms | 1,783 | 2026-09-24 |
| Hugging Face model configurations | Layers, key and value heads, head size and context length, the numbers the memory formula needs. | Terms | 953 | 2026-09-24 |
| Hugging Face GGUF file lists | The quantized files of a model and their sizes, from the GGUF copy its maker or the most downloaded copier publishes. | Terms | 712 | 2026-09-24 |
| models.dev | Direct provider prices, limits and capabilities, from a public database under the MIT licence. | Terms | 653 | 2026-09-24 |
| Baltor provider client records | Output limits that Baltor's own provider clients declare or observed, each with its day. | Terms | 7 | 2026-09-04 |
| Provider and runtime documentation | API styles, authentication, rate-limit, pricing and data-policy pages, read by a person on the day each fact names. | Terms | 17 | 2026-09-24 |
| Harness documentation | How OpenCode, Pi, Codex and Claude Code read a model provider, from each harness's own documentation. | Terms | 0 | Unknown |
- Ollama library: Linked only. Ollama's terms refuse automated access without permission, so no data is copied from it. Terms
Paid links
No link in this directory is a paid link or an ad, and no listing is paid for. The order and the contents of every list come from the sources named on this page.