Gemini Generate Content

POST

/v1beta/models/{model}:generateContent

Google Gemini native generateContent API. Use x-goog-api-key header or ?key= query parameter for authentication.

Supports text generation and image generation (for models like gemini-2.5-flash-image).
The request and response structure follows Google AI Studio API style; CCAPI only enhances authentication, proxy routing, and optional image URL rewriting.

Difference from Pay-per-image

This endpoint uses Gemini native contents / parts format

Uses native model names, e.g. gemini-2.5-flash-image

Can switch between base64 and url response format via image_response_format

Does not use the /v1/images/generations pay-per-image model name wrapping

Reference: https://ai.google.dev/gemini-api/docs/image-generation

Request

Authorization

API Key

Add parameter in header

Authorization

Example:

Authorization: ********************

Path Params

Query Params

Header Params

Body Params application/jsonRequired

Example

{
    "contents": [
        {}
    ],
    "generationConfig": {},
    "tools": [
        {}
    ]
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.ccapi.ai//v1beta/models/gemini-2.5-pro:generateContent?key' \
--header 'x-goog-api-key;' \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "contents": [
        {}
    ],
    "generationConfig": {},
    "tools": [
        {}
    ]
}'

Responses

🟢200success

application/json

Gemini response

Body

Example

{}

🟠400未认证

🟠401

🟠402

🟠403

🟠429

🔴500

Modified at 2026-03-15 06:56:57

How to Integrate CCAPI LLM into OpenClaw

Gemini Stream Generate Content

Gemini Generate Content

Difference from Pay-per-image#

Request

Request Code Samples

Responses

Difference from Pay-per-image