Gemini Chat - AiToEarn Open Platform

curl --request POST \ --url https://aitoearn.cn/api/ai/v1beta/models/{model}:generateContent \ --header 'Content-Type: application/json' \ --header 'x-goog-api-key: <api-key>' \ --data ' { "model": "<string>", "contents": [ { "parts": [ { "text": "<string>" } ] } ] } '

Authorizations

x-goog-api-key

string

header

required

API Key header used by Gemini SDK-compatible endpoints.

Path Parameters

model

string

required

Model ID. First call the "Conversation Model List" interface (GET /api/ai/models/chat) and pass in the data[n].name returned by it.

Body

application/json

model

string

required

Model ID, consistent with the path parameter model. The value comes from data[n].name returned by the "Conversation Model List" interface.

contents

object[]

required

Contents list

Hide child attributes

contents.parts

object[]

required

An ordered list of content fragments within a single message

Option 1
Option 2
Option 3

Hide child attributes

contents.parts.text

string

required

text fragment

contents.role

enum<string>

Message role, used to distinguish different message sources

Available options:

user,

model

config

object

Generate configuration

Hide child attributes

config.temperature

number

Controls the randomness of the output. The higher the value, the more divergent it is. The lower the value, the more stable it is.

config.topP

number

Kernel sampling parameters, limiting the maximum cumulative probability of tokens considered during sampling.

config.topK

number

Top-K sampling parameters, limiting the number of highest probability tokens considered during sampling

config.candidateCount

number

The number of candidate answers to be returned

config.maxOutputTokens

number

Maximum number of output tokens for candidate answers

config.responseLogprobs

boolean

Whether to return token logarithmic probability information

config.logprobs

number

The number of high-probability candidate tokens returned in each decoding step, only takes effect when responseLogprobs=true

config.presencePenalty

number

There is a penalty that is used to reduce or increase the tendency of tokens to appear again.

config.frequencyPenalty

number

Frequency penalty, which suppresses or encourages repetition based on the number of occurrences of the token

config.seed

number

Decode random seeds to improve output reproducibility

config.responseMimeType

string

expected response type

config.responseJsonSchema

any

JSON output structure constraints, usually used with responseMimeType=application/json

Response

Native third-party protocol response or SSE data, not wrapped in the AiToEarn common response envelope.

Native third-party protocol response, not wrapped in the AiToEarn common response envelope.