Skip to main content
Gemini 3.5 Flash-Lite is a cost-efficient multimodal model for high-volume, latency-sensitive text and media understanding workloads. Use 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

Pass this exact public ID in the top-level model field. Do not substitute an upstream provider alias.

​
Supported modes

  • chat_completions
  • responses_api
  • visual_understanding
  • text_generation

​
Inputs

  • Text
  • Image
  • Video
  • Audio

​
Outputs

  • Text

​
Capabilities

  • Not specified

​
Additional capabilities

  • Chat completions
  • Function calling
  • Code execution
  • Computer use
  • Responses API
  • Video understanding
  • SSE streaming
  • Structured output
  • Multimodal understanding
  • Configurable reasoning See Function calling and Gemini tools for tool declarations, result submission, and provider-specific capabilities.

​
Technical details

Availability and final customer prices can change. Check the Dashboard model catalog before production use.
See the API reference overview for authentication, request conventions, and response schemas.