Chat interface

POST

/v1/chat/completions

Given a hint, the model will return one or more complete predictions, and may also return the probability of an alternative label at each location.

Complete creation for the provided hint and parameters

Official documentation: https://ai.google.dev/gemini-api/docs/text-generation?hl=zh-cn

Request

Authorization

Bearer Token

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

Header Params

Body Params application/json

Examples

Responses

🟢200

application/json

Body

Request Example

Shell

JavaScript

Java

Swift

curl --location --request POST '/v1/chat/completions' \
--header 'Accept: application/json' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "messages": [
        {
            "role": "system",
            "content": "You'\''re a little pig. You'\''ll add a '\''hmph'\'' at the beginning of your replies."
        },
        {
            "role": "user",
            "content": "Who are you?"
        }
    ],
    "model": "gemini-2.5-pro",
    "temperature": 0.1,
    "top_p": 1,
    "stream": false
}'

Response Example

{
    "id": "string",
    "object": "string",
    "created": 0,
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "string",
                "content": "string"
            },
            "finish_reason": "string"
        }
    ],
    "usage": {
        "prompt_tokens": 0,
        "completion_tokens": 0,
        "total_tokens": 0
    }
}

Modified at 2026-02-08 10:33:33

Gemini-2.5-flash-all

Image recognition interface