Available models
Refer to the table on this page to see which base models Self-Serve Deployments supports. You can also deploy these models with LoRA adapters trained through Serverless Fine-Tuning.
For each model's pricing information, see pricing.
| MODEL | PROVIDER | TYPE | CONTEXT LENGTH | MULTI-LORA | LICENSE | ACCEPTABLE USE POLICY |
|---|---|---|---|---|---|---|
| deepseek-ai/DeepSeek-V4-Flash-0731 | DeepSeek | instruct | 1M | — | MIT License | |
| google/gemma-4-26b-a4b-it | instruct | — | — | Apache License 2.0 | ||
| google/gemma-4-31b-it | instruct | 262k | Yes | Apache License 2.0 | ||
| meta-llama/Llama-3.1-8B-Instruct | Meta | instruct | 131k | — | Llama 3.1 Community License Agreement | Llama 3.1 Acceptable Use Policy |
| meta-llama/Llama-3.3-70B-Instruct | Meta | instruct | 131k | — | Llama 3.3 Community License Agreement | Llama 3.3 Acceptable Use Policy |
| nvidia/nemotron-3.5-lightning-30b-a3b | NVIDIA | instruct | 262k | Yes | NVIDIA Nemotron Open Model License | NVIDIA Acceptable Use Terms |
| nvidia/nemotron-3.5-super-vl-120b-a12b | NVIDIA | instruct | 1M | — | NVIDIA Nemotron Open Model License | NVIDIA Acceptable Use Terms |
| openai/gpt-oss-20b | OpenAI | instruct | — |