Skip to main content

Available models

You can use the OpenAI-API compatible endpoint at api.inference.crusoecloud.com to access the models below for Serverless Inference. You can also interact with all of the models using the Intelligence Foundry's chat interface. All Meta models provided by Crusoe are "Built with Llama".

For each model's pricing information, see pricing.

MODELPROVIDERTYPECONTEXT LENGTHLICENSEACCEPTABLE USE POLICY
deepseek-ai/DeepSeek-V4-FlashDeepSeekinstruct1MMIT License
deepseek-ai/DeepSeek-V4-ProDeepSeekinstruct1MMIT License
google/gemma-4-31b-itGoogleinstruct262kApache License 2.0
moonshotai/Kimi-K2.6Moonshotinstruct256KModified MIT License
nvidia/Nemotron-3-Nano-30B-A3BNVIDIAinstruct262kNVIDIA Nemotron Open Model LicenseNVIDIA Acceptable Use Terms
nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3BNVIDIAinstruct262kNVIDIA Open Model Agreement
nvidia/Nemotron-3-Super-120B-A12BNVIDIAinstruct262kNVIDIA Nemotron Open Model LicenseNVIDIA Acceptable Use Terms
nvidia/Nemotron-3-VoiceChatNVIDIAspeech-to-speech131kNVIDIA Software and Model Evaluation LicenseNVIDIA Acceptable Use Terms
nvidia/nemotron-3.5-lightning-30b-a3bNVIDIAinstruct1MNVIDIA Nemotron Open Model LicenseNVIDIA Acceptable Use Terms
openai/gpt-oss-120bOpenAIinstruct128kApache License 2.0Acceptable Use Policy
qwen/Qwen3.8-27BQweninstruct256kApache License 2.0Apache License 2.0
zai/GLM-5.3Z.aiinstruct1MMIT License
zai/GLM-5.3-FlashZ.aiinstruct1MMIT License

Migrate from a deprecated model​

Five Serverless Inference models were deprecated on September 12, 2026.

To migrate from a deprecated model to a supported model:

  1. Update your API calls to use a recommended replacement model from the table below.
  2. Test the replacement model in your development environment.
Deprecated modelMigration path
Z.ai GLM-5.1Z.ai GLM-5.3
Z.ai GLM-5.2Z.ai GLM-5.3
DeepSeek V3DeepSeek V4 Pro or DeepSeek V4 Flash
Qwen3 235B A22BDeepSeek V4 Flash or Qwen 3.8 27B
Llama 3.3 70BDeepSeek V4 Flash

For the current list of supported models, see Available models.