1 Million token context window

Gemini API
1M context, 16 models

Gemini 2.5 Pro for deep analysis. Gemini 2.5 Flash for speed. Plus GPT, Claude, DeepSeek through the same endpoint.

Start free — 50 API calls

Gemini 2.5 Pro

Google flagship. 1M context window, strong reasoning and vision.

$1.63/ M input

$13.00/ M output

Model ID: google/gemini-2.5-pro

Gemini 2.5 Flash

Fast and cheap. 1M context, vision supported.

$0.13/ M input

$0.52/ M output

Model ID: google/gemini-2.5-flash

Use Gemini with OpenAI SDK

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aipower.me/v1",
    api_key="YOUR_API_KEY",
)

# Gemini 2.5 Pro — 1M context for entire codebases
response = client.chat.completions.create(
    model="google/gemini-2.5-pro",
    messages=[{"role": "user", "content": long_document}],
)

# Gemini 2.5 Flash — fast and cheap
response = client.chat.completions.create(
    model="google/gemini-2.5-flash",
    messages=[{"role": "user", "content": "Quick question"}],
)

1M context: what can you do?

Analyze entire codebases

Feed a full repository into one API call. Understand architecture, find bugs, suggest improvements.

Process full books

Summarize, Q&A, or analyze 400+ page documents in a single request.

Cross-reference research

Compare 50+ papers simultaneously. Find connections across large datasets.

Long conversation memory

Maintain context across thousands of exchanges without forgetting earlier details.

Try Gemini API now

50 free API calls. 1M context window. OpenAI SDK compatible.

Get free API key

Gemini API1M context, 16 models