gemini-3.5-flash API

Gemini 3.5 Flash is the flagship of Google's Flash line — the tier historically built for speed and cost efficiency — but this generation closes most of the gap to the Pro models. Google positions it for sustained frontier performance on agentic and coding tasks, and it shows: the model holds up over long multi-step coding sessions instead of degrading after the first few turns, which older Flash releases were prone to do. It keeps the line's trademark low time-to-first-token, so it feels responsive in interactive use even on large prompts. The headline spec is context: 1,048,576 input tokens and up to 65,536 output tokens. That is enough to load an entire mid-sized repository, a full book, or hundreds of pages of reports into a single request and still leave generous room for the answer. Combined with vision input, it handles mixed workloads — code plus screenshots, contracts plus scanned tables — without splitting the job across models. One billing note worth knowing: the model can spend internal reasoning ("thinking") tokens before answering, and those are counted at the output rate, so terse-looking answers on hard problems may bill more output tokens than the visible text suggests. At $1.50/$9.00 per 1M tokens, it sits well above the budget Flash variants but below Pro-class pricing — the right slot when you need near-frontier quality at interactive latency and batch-friendly cost. On CaMeL Hub you can reach it three ways with the same key: the OpenAI-compatible endpoint (drop-in for existing SDK code), the Gemini-native endpoint, and an Anthropic-compatible endpoint, so whichever client library your stack already uses will work without a rewrite.

curl https://api.camel-hub.com/v1/chat/completions \
  -H "Authorization: Bearer $CAMEL_HUB_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.5-flash",
    "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-3.5-flash",
    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-3.5-flash",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);