Gemini 3.7 Flash API: now on FastMetal
Google's Gemini 3.7 Flash (gemini-3.7-flash) is available on FastMetal. It succeeds Gemini 3.5 Flash, which stays in the catalog, and Google built it for fast agent workflows and coding.
What you get
- Speed with reliable multi-step work: Google's focus for this release is response speed and dependable tool-using loops.
- A context window of about 1.05M tokens, enough for long documents and large codebases.
- Image input alongside text. File (PDF) input is refused on FastMetal's route for this model, because the upstream drops the file without reading it.
- Flash-tier cost: it sits in Google's lower-cost line. Current rates are on the model page.
Calling it
curl https://api.fastmetal.ai/v1/chat/completions \
-H "Authorization: Bearer $FASTMETAL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.7-flash",
"messages": [{"role": "user", "content": "Hello"}]
}'
The request is the same as for any other model, so moving from gemini-3.5-flash means changing the model value. To try it without code, pick it in chat.
How it compares
Gemini 3.7 Flash vs GPT-5.6 Luna puts it beside OpenAI's fast tier on the same prompts.
Pricing
Billed per million input and output tokens, with cache reads and writes billed per million tokens too, from a prepaid balance. Current rates are on pricing and the model pages in the catalog.