Models
The models we track, their specs, and which hosting plans offer them.
| Model | Developer | Parameters | Context | License | Hosting plans |
|---|---|---|---|---|---|
| DeepSeek-V3 | DeepSeek | 671B total, 37B active (mixture of experts) | 128K tokens | DeepSeek Model License | 4 |
| gpt-oss-120b | OpenAI | 117B total, about 5B active (mixture of experts) | 128K tokens | Apache 2.0 | 5 |
| Llama 3.1 8B Instruct | Meta | 8B | 128K tokens | Llama 3.1 Community License | 6 |
| Llama 3.3 70B Instruct | Meta | 70B | 128K tokens | Llama 3.3 Community License | 7 |
| Qwen2.5 72B Instruct | Alibaba Cloud (Qwen team) | 72B | Up to 128K tokens | Qwen License | 5 |