gemini-2.5-pro API

Gemini 2.5 Pro is the most capable model in Google's 2.5 generation: a thinking model that reasons through a problem before it answers. That design shows up most clearly on hard coding tasks, multi-step math, and analysis that spans very long inputs — its 1,048,576-token input limit comfortably holds an entire codebase, a set of contracts, or several research papers in one prompt, and it can return up to 65,536 output tokens in a single response. On cost, it sits in the middle of the market: far below top-priced frontier flagships, but above the fast Flash-class models. The base rate is $1.25 per 1M input tokens and $10.00 per 1M output tokens. Pricing is segmented by prompt size — once a single prompt exceeds 200K tokens, that request is billed at the long-context tier of $2.50 input / $15.00 output per 1M. If you routinely feed it near-window-sized inputs, it is worth chunking work below the 200K boundary where possible. On CaMeL Hub you can reach gemini-2.5-pro two ways: through the OpenAI-compatible /v1/chat/completions endpoint (keep your existing OpenAI SDK, change only base_url and the model name) or through a Gemini-native endpoint if you prefer Google's request format. Streaming, image input, function calling, and web-search grounding are all supported. One behavior to plan for: because the model spends internal "thinking" tokens before emitting text, time-to-first-token is noticeably longer than on non-reasoning models, and those thinking tokens are counted as output tokens in usage.

curl https://api.camel-hub.com/v1/chat/completions \
  -H "Authorization: Bearer $CAMEL_HUB_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-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-2.5-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-2.5-pro",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);