Gemini API — AI Chat & Reasoning API | OpenAI-Compatible, Free Credits

Provider

Google

Pricing

~5 credits pre-deduct, pay-per-token

Speed

1–5 seconds

Output

text

Quick Start

Send a request to the Gemini API:

bash

1	curl -X POST https://apiin.one/api/v1/chat/completions \
2	-H "Authorization: Bearer YOUR_API_KEY" \
3	-H "Content-Type: application/json" \
4	-d '{
5	"model": "gemini",
6	"messages": [
7	{
8	"role": "user",
9	"content": "Explain quantum computing in simple terms."
10	}
11	],
12	"stream": false,
13	"include_thoughts": true
14	}'

API Endpoint

POST/api/v1/chat/completionsGemini

Send a POST request with your API key to generate content using Gemini.

Headers

Body ParametersJSON

Authorization:string

Bearer YOUR_API_KEY

Content-Type:string

application/json

Body Parameters

Body ParametersJSON

model:string

Model identifier: gemini

messages:array

Array of message objects with role (user/assistant/system/developer) and content

stream:optional boolean

Enable SSE streaming responses Defaults to true.

include_thoughts:optional boolean

Include model reasoning/thinking steps Defaults to true.

reasoning_effort:optional string

Reasoning depth: low or high Defaults to high.

tools:optional array

Tool definitions for function calling (OpenAI-compatible format)

response_format:optional object

Force structured output (e.g. {type: json_object})

Example Request

json

1	{
2	"model": "gemini",
3	"messages": [
4	{
5	"role": "user",
6	"content": "Explain quantum computing in simple terms."
7	}
8	],
9	"stream": false,
10	"include_thoughts": true
11	}

Example Response

Successful completion response.

1	{
2	"code": 200,
3	"message": "success",
4	"data": {
5	"id": "chatcmpl_mno345",
6	"model": "gemini-3-flash",
7	"choices": [
8	{
9	"message": {
10	"role": "assistant",
11	"content": "Quantum computing uses quantum bits (qubits)..."
12	}
13	}
14	],
15	"usage": {
16	"prompt_tokens": 12,
17	"completion_tokens": 156,
18	"total_tokens": 168
19	},
20	"credits_consumed": 2,
21	"task_id": "n62xxxx_chat"
22	}
23	}

Use Cases

✓Build AI-powered chatbots and customer support agents
✓Generate and summarize text content at scale
✓Create AI coding assistants and code generation tools
✓Power reasoning and analysis features in your application

API Tester

Test the Gemini API directly from your browser:

API-PlaygroundPOST

Basis-URL

Endpunkt

Header

Request-Body

Error Codes

1	{
2	"error": {
3	"code": 400,
4	"message": "Invalid parameters",
5	"type": "invalid_request"
6	}
7	}

Frequently Asked Questions

Is the Gemini API compatible with OpenAI's format?

Yes. API in One uses the standard OpenAI chat/completions format. You can switch from OpenAI to Gemini by changing the base URL and model name — no other code changes needed.

How much does the Gemini API cost?

5 credits are pre-deducted per request, then adjusted based on actual token usage (pay-per-token). One of the most affordable LLM APIs. Free credits included on sign up.