gemini-3.1-flash-lite

GoogleToken-based

Alias:gemini-3.1-flash-lite-preview

Google 的 gemini-3.1-flash-lite 模型，支持文本、图像、音频、视频、文件输入和文本输出。支持推理、工具调用、结构化输出。

textimageaudiovideofilecachingcode_interpreterfunction_callingtoolsweb_searchstructured_outputjson_modereasoningvisioncontext:1048576

API access

RequestPOST/v1beta/models/gemini-3.1-flash-lite:generateContent

Example request

Parameters

Parameter	Type	Default / range	Description
`temperature`	number	=`1`0 ~ 2	Sampling temperature; lower is more deterministic
`top_p`	number	=`1`0 ~ 1	Nucleus sampling probability mass
`max_tokens`	integer	>= 1	Maximum number of tokens in the response
`frequency_penalty`	number	=`0`-2 ~ 2	Penalises repetition of frequent tokens
`presence_penalty`	number	=`0`-2 ~ 2	Encourages introducing new topics
`stop`	array	—	Up to 4 strings that stop generation
`seed`	integer	—	Deterministic sampling seed (best-effort)
`n`	integer	=`1`>= 1	Number of completions to generate
`stream`	boolean	=`false`	Stream tokens via Server-Sent Events
`response_format`	object	—	Force JSON object or schema-conforming output
`tools`	array	—	Tool / function declarations the model may call
`tool_choice`	string	`autononerequired`	Tool-choice policy or specific tool name
`logprobs`	boolean	=`false`	Return per-token log probabilities
`top_logprobs`	integer	0 ~ 20	Number of top log probabilities returned per token
`logit_bias`	object	—	Per-token logit bias map
`user`	string	—	End-user identifier for abuse monitoring

Replace <YOUR_API_KEY> with the API key from your token settings.

All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.

Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.

Generation parameters

Parameter	Type	Default / range	Description
`temperature`	number	=`1`0 ~ 2	Sampling temperature; lower is more deterministic
`top_p`	number	=`1`0 ~ 1	Nucleus sampling probability mass
`max_tokens`	integer	>= 1	Maximum number of tokens in the response
`frequency_penalty`	number	=`0`-2 ~ 2	Penalises repetition of frequent tokens
`presence_penalty`	number	=`0`-2 ~ 2	Encourages introducing new topics
`stop`	array	—	Up to 4 strings that stop generation
`seed`	integer	—	Deterministic sampling seed (best-effort)
`n`	integer	=`1`>= 1	Number of completions to generate
`stream`	boolean	=`false`	Stream tokens via Server-Sent Events
`response_format`	object	—	Force JSON object or schema-conforming output
`tools`	array	—	Tool / function declarations the model may call
`tool_choice`	string	`autononerequired`	Tool-choice policy or specific tool name
`logprobs`	boolean	=`false`	Return per-token log probabilities
`top_logprobs`	integer	0 ~ 20	Number of top log probabilities returned per token
`logit_bias`	object	—	Per-token logit bias map
`user`	string	—	End-user identifier for abuse monitoring

Supplier	RPM	TPM	RPD
Google AI Studio	920	369K	19K
Google Vertex	550	219K	11K

RPM = requests per minute, TPM = tokens per minute, RPD = requests per day. Limits apply per token group.