gemini-3.1-pro API

Gemini 3.1 Pro is the top model of Google's Gemini 3.1 line, built for complex problem-solving, agentic workflows, and serious coding work. It is a thinking model: it reasons internally before producing an answer, which noticeably improves results on multi-step planning, math, and hard debugging compared with flash-class models — at the cost of some additional output tokens, since reasoning tokens are billed as output. It accepts images alongside text, calls functions reliably enough to drive multi-tool agents, and can ground answers with web search. Its defining spec is scale: a 1,048,576-token input window with up to 65,536 output tokens, both documented by Google. That is enough to hold an entire mid-sized codebase, a full legal document set, or hundreds of pages of research in a single request. Pricing is segmented by prompt size: requests up to 200K prompt tokens bill at $2.00 per 1M input and $12.00 per 1M output tokens, while anything above 200K moves to $4.00 / $18.00. In practice that puts Gemini 3.1 Pro in the value sweet spot for long-context work — flagship-grade reasoning without Opus-class prices, and one of the cheapest ways to run 500K+-token prompts at all. On CaMeL Hub the model is exposed on two endpoints: the OpenAI-compatible chat completions API (change base_url to https://api.camel-hub.com/v1, keep your existing OpenAI SDK code) and the native Gemini API format for tools that speak it directly. Streaming works on both. You top up with Alipay, WeChat Pay, or international cards, or pick a subscription plan — no Google Cloud project, billing account, or region workarounds required.

curl https://api.camel-hub.com/v1/chat/completions \
  -H "Authorization: Bearer $CAMEL_HUB_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-pro",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="$CAMEL_HUB_KEY",
    base_url="https://api.camel-hub.com/v1",  # <-- the only change vs. the OpenAI default
)

resp = client.chat.completions.create(
    model="gemini-3.1-pro",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.CAMEL_HUB_KEY,
  baseURL: "https://api.camel-hub.com/v1", // <-- the only change vs. the OpenAI default
});

const resp = await client.chat.completions.create({
  model: "gemini-3.1-pro",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);