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 LENGTHMULTI-LORALICENSEACCEPTABLE USE POLICY
deepseek-ai/DeepSeek-V4-Flash-0731DeepSeekinstruct1M—MIT License
google/gemma-4-26b-a4b-itGoogleinstruct——Apache License 2.0
google/gemma-4-31b-itGoogleinstruct262kYesApache License 2.0
meta-llama/Llama-3.1-8B-InstructMetainstruct131k—Llama 3.1 Community License AgreementLlama 3.1 Acceptable Use Policy
meta-llama/Llama-3.3-70B-InstructMetainstruct131k—Llama 3.3 Community License AgreementLlama 3.3 Acceptable Use Policy
nvidia/nemotron-3.5-lightning-30b-a3bNVIDIAinstruct262kYesNVIDIA Nemotron Open Model LicenseNVIDIA Acceptable Use Terms
nvidia/nemotron-3.5-super-vl-120b-a12bNVIDIAinstruct1M—NVIDIA Nemotron Open Model LicenseNVIDIA Acceptable Use Terms
openai/gpt-oss-20bOpenAIinstruct——Apache License 2.0Acceptable Use Policy
openai/gpt-oss-120bOpenAIinstruct131k—Apache License 2.0Acceptable Use Policy
qwen/Qwen3-8BQweninstruct—YesApache License 2.0Apache License 2.0
qwen/Qwen3-235B-A22B-Instruct-2507Qweninstruct262k—Apache License 2.0Apache License 2.0
qwen/Qwen3.5-2BQweninstruct—YesApache License 2.0Apache License 2.0
qwen/Qwen3.5-9BQweninstruct262kYesApache License 2.0Apache License 2.0
qwen/Qwen3.5-35B-A3BQweninstruct——Apache License 2.0Apache License 2.0
qwen/Qwen3.6-27BQweninstruct262kYesApache License 2.0Apache License 2.0
qwen/Qwen3.6-35B-A3BQweninstruct262kYesApache License 2.0Apache License 2.0
qwen/Qwen3.8-27BQweninstruct262kYesApache License 2.0Apache License 2.0
thinkingmachines/Inkling-SmallThinking Machines Labsinstruct1M—Apache License 2.0Apache License 2.0
zai-org/GLM-5.2Z.aiinstruct1M—MIT License
zai-org/GLM-5.3Z.aiinstruct262k (H200), 1M—GLM 5.3 License
zai-org/GLM-5.3-FlashZ.aiinstruct1M—MIT License