gemini-3-flash API

Gemini 3 Flash is the speed-and-cost tier of Google's Gemini 3 generation, positioned by Google as delivering frontier-class performance rivaling much larger models at a fraction of the cost. It pairs a 1,048,576-token input context with up to 65,536 output tokens, which puts it in a small club of models that can ingest entire codebases, book-length documents, or hours of meeting transcripts in a single request while still being priced for high-volume production traffic. The pricing shape matters as much as the headline numbers: input tokens cost $0.50 per million while output costs $3.00 per million, a 6x spread. That asymmetry makes Gemini 3 Flash especially economical for prompt-heavy workloads — RAG pipelines that stuff large retrieved contexts, document analysis where you feed hundreds of pages and get back a short structured answer, or classification jobs where output is a few tokens. Workloads that generate long-form output pay proportionally more, so it is worth estimating your input:output ratio before comparing it against alternatives. On CaMeL Hub, Gemini 3 Flash is exposed through two endpoint styles: the OpenAI-compatible /v1/chat/completions route (works with the official OpenAI SDKs in Python, Node.js, and any tool that lets you override base_url) and a Gemini-native route for clients built against Google's request format. Streaming responses, image/vision input, and function calling are all supported, so it drops into existing agent frameworks and chat UIs without code changes beyond the base URL and API key.

curl https://api.camel-hub.com/v1/chat/completions \
  -H "Authorization: Bearer $CAMEL_HUB_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-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-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-flash",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);