Gemini 3.1 Pro Preview

Gemini 3.1 Pro preview, 200K+ 上下文 + thinking

Model ID: gemini-3.1-pro-preview · Type: chat · Provider: Google

Endpoints: /v1/chat/completions · /v1/messages

Pricing

Input (per 1M tokens)$1.5 USD
Output (per 1M tokens)$9 USD
Cache read (per 1M tokens)$0.15 USD

Context tiers

≤ 200000 tokens$1.5 / 1M in$9 / 1M out
> 200000$3 / 1M in$13.5 / 1M out

Capabilities

from openai import OpenAI

client = OpenAI(api_key="sk-...", base_url="https://api.router.ai/v1")
resp = client.chat.completions.create(
    model="gemini-3.1-pro-preview",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

FAQ

How much does Gemini 3.1 Pro Preview cost on 370.AI?

Gemini 3.1 Pro Preview (`gemini-3.1-pro-preview`) is billed per usage at $1.5/1M in · $9/1M out, in USD. Current pricing is always listed at https://www.370.ai/models/gemini-3.1-pro-preview.

How do I call Gemini 3.1 Pro Preview through 370.AI?

Send a request to https://api.router.ai/v1/v1/chat/completions with the header `Authorization: Bearer <your API key>` and `"model": "gemini-3.1-pro-preview"`. The API is OpenAI-compatible, so any OpenAI SDK works by changing base_url to https://api.router.ai/v1 — no other code change.

Which endpoints does Gemini 3.1 Pro Preview support?

Gemini 3.1 Pro Preview can be called on: /v1/chat/completions; /v1/messages.

What is Gemini 3.1 Pro Preview's context window?

Gemini 3.1 Pro Preview accepts up to 1,048,576 input tokens and can return up to 65,536 output tokens. Requests exceeding the input limit are rejected before reaching the model.

What can Gemini 3.1 Pro Preview do?

Gemini 3.1 Pro Preview supports: vision, function_calling, prompt_caching, audio_input, thinking, long_context, cache.

Who makes Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview is a chat model from Google, available through the 370.AI gateway with the same API key as every other model.

Call it through the 370.AI OpenAI-compatible endpoint (API base: https://api.router.ai/v1). AI agents can discover and call every model on this gateway through MCP (https://mcp.router.ai/mcp) with no manual integration.

API reference · All models