Skip to main content

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.

MODELPROVIDERTYPECONTEXT LENGTHLICENSEACCEPTABLE USE POLICY
deepseek-ai/DeepSeek-V4-FlashDeepSeekinstruct1MMIT License
google/gemma-4-31b-itGoogleinstruct262kApache License 2.0
meta-llama/Llama-3.1-8B-InstructMetainstruct—Llama 3.1 Community License AgreementLlama 3.1 Acceptable Use Policy
meta-llama/Llama-3.3-70B-InstructMetainstruct131kLlama 3.3 Community License AgreementLlama 3.3 Acceptable Use Policy
nvidia/nemotron-3.5-lightning-30b-a3bNVIDIAinstruct1MNVIDIA Nemotron Open Model LicenseNVIDIA Acceptable Use Terms
openai/gpt-oss-20bOpenAIinstruct—Apache License 2.0Acceptable Use Policy
openai/gpt-oss-120bOpenAIinstruct131kApache License 2.0Acceptable Use Policy
qwen/Qwen3-8BQweninstruct—Apache License 2.0Apache License 2.0
qwen/Qwen3-235B-A22BQweninstruct262kApache License 2.0Apache License 2.0
qwen/Qwen3.5-2BQweninstruct—Apache License 2.0Apache License 2.0
qwen/Qwen3.5-9BQweninstruct—Apache License 2.0Apache License 2.0
qwen/Qwen3.6-35B-A3BQweninstruct—Apache License 2.0Apache License 2.0
zai/GLM-5.2Z.aiinstruct1MMIT License