Skip to main content
POST
Chat completion: Gemini 3.5 Flash-Lite (OpenAI-compatible)
Use the playground on the right: put Bearer sk-your-api-key in Authorization and hit send — no thinking by default, so responses are fast.
For deep reasoning pass reasoning_effort: "high" (note: this endpoint does not report reasoning_tokens for this model — use the Native Playground for precise thinking observation). Search grounding, code execution, and other native tools are not available on this endpoint. Overview and measured data: Gemini 3.5 Flash-Lite Overview.

Parameter quick reference

Response notes

  • usage.completion_tokens_details.reasoning_tokens is not reported for this model (3.6 Flash does report it) — thinking spend is folded into completion_tokens
  • Thinking text (reasoning_content) is not echoed on this endpoint
  • Double-check the model name gemini-3.5-flash-lite (three lowercase segments, hyphenated)

Authorizations

Authorization
string
header
required

Add Authorization: Bearer YOUR_API_KEY header

Body

application/json
model
string
required

Fixed: gemini-3.5-flash-lite

messages
object[]
required

Standard OpenAI messages array

max_tokens
integer

Output quota; 2000+ recommended with thinking on (thinking bills as output)

temperature
number
stream
boolean

SSE streaming

reasoning_effort
enum<string>

Thinking tier

Available options:
low,
medium,
high
response_format
object

Structured output, json_schema supported

tools
object[]

Function-calling tool list

Response

Success

id
string
model
string
choices
object[]
usage
object

Usage stats