Gemini

Tempo

Llm3 endpointsDynamic pricing

Google's Gemini LLM API. Text and image generation with Gemini 2.0 Flash (fast), 2.5 Flash (improved reasoning), and 2.5 Pro (most capable). Multimodal input support — text, images, and code.

View documentation

When should an agent use this?

Use Gemini when your agent needs an LLM for text generation, code generation, analysis, or image understanding — and you want Google's models specifically. Ideal for agents that need fast responses (2.0 Flash), improved reasoning (2.5 Flash), or maximum capability (2.5 Pro). Works well for summarization, Q&A, code review, and multimodal tasks.

Endpoints

Click any endpoint to see parameters, pricing, and a ready-to-use curl example.

Paid (3)

Gemini 2.0 Flash — fast, efficient multimodal model for text and image generation.

Path/services/gemini/v1beta/models/gemini-2.0-flash:generateContent

MethodPOST

PriceDynamic (varies per request)

Parameters

Name	Type	Required	Description
contents	array	Yes	Array of content objects with parts (text, image, etc.)
generationConfig	object	No	Optional config — temperature, maxOutputTokens, topP, topK

Example Request

curl

curl -X POST \
  "https://api.indiegent.com/services/gemini/v1beta/models/gemini-2.0-flash:generateContent" \
  -H "Authorization: Bearer <your-token>" \
  -H "X-Agent-Wallet: my-agent" \
  -H "Content-Type: application/json" \
  -d '{
  "contents": [{"parts": [{"text": "Explain how blockchain consensus mechanisms work in simple terms"}]}]
}'

IndieGent Endpoint

api.indiegent.com/services/gemini

Payment

USDC · Automatic

Payment protocols handled by IndieGent

Network

Tempo

Get Started ← Back to Ecosystem Browse Marketplace →