Gemini 3.5 Fast API
Low-latency Gemini for coding agents and chat apps.
Run gemini-3.5-fast through a drop-in OpenAI-compatible endpoint. Metered price is $0.90 input / $5.40 output per million tokens, billed through one Hypereal API key.
Independent third-party API aggregator. Not affiliated with or endorsed by any model provider; model names are trademarks of their respective owners.
Gemini 3.5 Fast pricing
Hypereal public token pricing
Integrate in minutes
Standard REST API that works with any language. One API key gives you access to all models.
- Single endpoint for all models
- Bearer token authentication
- JSON request & response
- Webhook callbacks for async jobs
- Python & Node.js SDK available
curl https://api.hypereal.cloud/v1/chat/completions \
-H "Authorization: Bearer hyp-..." \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.5-fast",
"messages": [
{"role": "user", "content": "Generate unit tests for this parser."}
]
}'Why Gemini 3.5 Fast
metered pricing eligible
Spend metered pricing credits on Gemini 3.5 Fast alongside Claude Opus, Sonnet, and GPT-5.5 — one prepaid pool, one API key.
Built for latency and volume
Sub-second first token — best for quick code review, chat, test generation, and iterative agent loops.
Current metered pricing
$0.90 input / $5.40 output per million tokens through Hypereal Credits. No Google Cloud project or separate billing account required.
Frequently asked questions
Is Gemini 3.5 Fast included in the metered pricing?
Yes. It is eligible for metered pricing credits, so prepaid Hypereal Credits spend on it just like Claude Opus, Sonnet, and GPT-5.5.
What is the model ID?
Use gemini-3.5-fast in chat, /v1/chat/completions, and any OpenAI-compatible SDK call.
When should I use Fast instead of Thinking?
Use Fast for latency-sensitive coding loops, tests, and chat. Use Thinking for deeper review or multi-step reasoning. Both cost the same per token.
Use Gemini 3.5 Fast with Hypereal Credits.
Create an API key, set base_url to Hypereal, and call gemini-3.5-fast from OpenAI-compatible tools.