minimal reasoning for extraction and other straightforward tasks. The model defaults to minimal; low, medium, and high are also supported.
Custom temperature, top_p, and top_k values are ignored. frequency_penalty and presence_penalty are not supported, and the final non-system message must not use the assistant role.
Model ID
model field.
Supported modes
chat_completionsresponses_apivisual_understandingtext_generation
Inputs
TextImageVideoAudio
Outputs
Text
Capabilities
- Not specified
Additional capabilities
Chat completionsFunction callingCode executionComputer useResponses APIVideo understandingSSE streamingStructured outputMultimodal understandingConfigurable reasoningSee Function calling for tool declarations and result submission.
Technical details
Availability and final customer prices can change. Check the Dashboard model catalog before production use.