Directory
Models, open and hosted
Context windows, prices, licences, quantizations and hardware needs for 2,342 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 2,342 models.
- 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
- 0.239 USD
- Kimi-K2.6moonshotai
- Parameters
- 1.0T
- Context
- 262,144
- Licence
- other
- Input, per million tokens
- 0.450 USD
- Kimi-K2.7-Codemoonshotai
- Parameters
- 1.0T
- Context
- 262,144
- Licence
- other
- Input, per million tokens
- 0.660 USD
- gemma-4-31B-itgoogle
- Parameters
- 31.3B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.100 USD
- Qwen3.8-27BQwen
- Parameters
- 27.8B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.040 USD
- gpt-oss-20bopenai
- Parameters
- 20.9B
- Context
- 131,072
- Licence
- apache-2.0
- Input, per million tokens
- 0.018 USD
- GLM-5.2zai-org
- Parameters
- 753.3B
- Context
- 1,048,576
- Licence
- mit
- Input, per million tokens
- 0.620 USD
- Qwen3.5-397B-A17BQwen
- Parameters
- 403.4B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.172 USD
- Llama-3.3-70B-Instructmeta-llama
- Parameters
- 70.6B
- Context
- 131,072
- Licence
- llama3.3
- Input, per million tokens
- 0.050 USD
- Inklingthinkingmachines
- Parameters
- 952.4B
- Context
- Unknown
- Licence
- apache-2.0
- Input, per million tokens
- 0.950 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
- Kimi-K2.5moonshotai
- Parameters
- 1.0T
- Context
- 262,144
- Licence
- other
- Input, per million tokens
- 0.375 USD
- GLM-5.3-Flashzai-org
- Parameters
- 321.3B
- Context
- 1,048,576
- Licence
- mit
- Input, per million tokens
- 0.100 USD
- GLM-5.3zai-org
- Parameters
- 753.3B
- Context
- 1,048,576
- Licence
- other
- Input, per million tokens
- 0.340 USD
- Qwen3-235B-A22B-Instruct-2507Qwen
- Parameters
- 235.1B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.087 USD
- gemma-4-26B-A4B-itgoogle
- Parameters
- 25.8B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.042 USD
- Qwen3.5-122B-A10BQwen
- Parameters
- 125.1B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.115 USD
- DeepSeek-V4-Flash-0731deepseek-ai
- Parameters
- 304.2B
- Context
- 1,048,576
- Licence
- mit
- Input, per million tokens
- 0.060 USD
- Hy3tencent
- Parameters
- 298.8B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.066 USD
- MiniMax-M3MiniMaxAI
- Parameters
- 427.0B
- Context
- 1,048,576
- Licence
- other
- Input, per million tokens
- 0.230 USD
- DeepSeek-V4-Flashdeepseek-ai
- Parameters
- 290.9B
- Context
- 1,048,576
- Licence
- mit
- Input, per million tokens
- 0.090 USD
- DeepSeek-V4-Prodeepseek-ai
- Parameters
- 1.6T
- Context
- 1,048,576
- Licence
- mit
- Input, per million tokens
- 0.435 USD
- Qwen3.5-35B-A3BQwen
- Parameters
- 36.0B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.057 USD
- Kimi-K2-Thinkingmoonshotai
- Parameters
- 1.0T
- Context
- 262,144
- Licence
- other
- Input, per million tokens
- 0.550 USD
- Hy4-previewtencent
- Parameters
- 780.0B
- Context
- 1,048,576
- Licence
- apache-2.0
- Input, per million tokens
- 0.834 USD
- Qwen3.8-2.4T-A95BQwen
- Parameters
- 2.4T
- Context
- 262,144
- Licence
- other
- Input, per million tokens
- 1.95 USD
- Inkling-Smallthinkingmachines
- Parameters
- 266.0B
- Context
- Unknown
- Licence
- apache-2.0
- Input, per million tokens
- 0.450 USD
- Qwen3.5-9BQwen
- Parameters
- 9.7B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.050 USD
- Qwen3.5-27BQwen
- Parameters
- 27.8B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.086 USD
- DeepSeek-V4-Pro-0813deepseek-ai
- Parameters
- 1.7T
- Context
- 1,048,576
- Licence
- mit
- Input, per million tokens
- 0.600 USD
- GLM-5.1zai-org
- Parameters
- 753.9B
- Context
- 202,752
- Licence
- mit
- Input, per million tokens
- 0.615 USD
- MiniMax-M2.5MiniMaxAI
- Parameters
- 228.7B
- Context
- 196,608
- Licence
- other
- Input, per million tokens
- 0.150 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-ai
- Parameters
- 684.5B
- Context
- 163,840
- Licence
- mit
- Input, per million tokens
- 0.200 USD
- Qwen3-32BQwen
- Parameters
- 32.8B
- Context
- 40,960
- Licence
- apache-2.0
- Input, per million tokens
- 0.080 USD
- DeepSeek-V4.1-Flashdeepseek-ai
- Parameters
- 763.2B
- Context
- 1,048,576
- Licence
- mit
- Input, per million tokens
- 0.090 USD
- Qwen3-VL-30B-A3B-InstructQwen
- Parameters
- 31.1B
- Context
- 262,144
- Licence
- apache-2.0
- Input, per million tokens
- 0.150 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 republishes only sources whose licence or terms allow it. It was built on .
| Source | What it gives | Licence or terms | Rows | Last read |
|---|---|---|---|---|
| Hugging Face Hub API | Licence, parameter count, publication date, downloads and task of open models, read within the API's published request limit. | Terms of service; each model card declares its own licence, checked | 2,018 | 2026-10-20 |
| Hugging Face model configurations | Layers, key and value heads, head size and context length, the numbers the memory formula needs. | Terms of service, checked | 825 | 2026-10-20 |
| 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 of service, checked | 607 | 2026-10-20 |
| models.dev | Provider prices with each record's own date, the limits and capabilities of the makers' own APIs, release dates, and each provider's documented address and key variable. | MIT, checked | 804 | 2026-10-20 |
| LiteLLM model price and context file | Provider prices as listed on the day the file was read, and the input and output limits and tool calling, structured output and reasoning flags of the makers' own APIs. | MIT, checked | 353 | 2026-10-20 |
| LMArena leaderboard dataset | The overall text arena score with style control from the latest leaderboard, rounded to a whole number, for a hosted model the arena names with its maker's own identifier. | CC BY 4.0, checked | 69 | 2026-10-19 |
| Baltor provider client records | Output limits that Baltor's own provider clients declare or observed, each with its day. | Baltor's own record, checked | 7 | 2026-09-04 |
| Provider and runtime documentation | API styles, authentication, structured output, tool calling, rate-limit, pricing and data-policy pages, read by a person on the day each fact names. | Baltor's own record of each provider's public pages, checked | 17 | 2026-09-27 |
| Harness documentation | How OpenCode, Pi, Codex and Claude Code read a model provider, from each harness's own documentation. | Baltor's own record of each harness's documentation, checked | 0 | Unknown |
Linked, never copied:
- Ollama library: Linked only. Ollama's terms refuse automated access without permission, so no data is copied from it. Terms
- OpenRouter: Linked only. OpenRouter's terms of August 31, 2026 forbid copying information on its site or services by script and using it for a competing service, so none of its prices, limits or rankings are copied here. It documents a Models API that your own tool can read with your own account. Terms
- Artificial Analysis: Linked only. Its website terms allow only personal, noncommercial use, so none of its indexes, prices or speed measurements are copied here. 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.