Gemini 3.8 Flash API: now on FastMetal
Google's Gemini 3.8 Flash (gemini-3.8-flash) is available on FastMetal. It follows Gemini 3.7 Flash, and Google names software development, agent work and multi-step reasoning as the areas it improves.
What you get
- The same per-token rates as Gemini 3.7 Flash, for input and output. Moving to 3.8 does not raise the bill.
- A 1,048,576-token context.
- Image, video and file input alongside text. We have tested image input through FastMetal.
- Reasoning effort per request: set
reasoning.efforttolow,mediumorhigh. With nothing set, it usesmedium. Reasoning tokens are billed as output tokens, solowsuits simple conversion and classification jobs. See the reasoning guide.
Calling it
curl https://api.fastmetal.ai/v1/chat/completions \
-H "Authorization: Bearer $FASTMETAL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.8-flash",
"messages": [{"role": "user", "content": "Hello"}],
"reasoning": {"effort": "low"}
}'
Already on Gemini 3.7 Flash? Change the model value and you are done. Gemini 3.7 Flash stays available, so you can run both side by side while you check the results. To try 3.8 without code, pick it in chat.
3.7 Flash vs 3.8 Flash
Gemini 3.7 Flash vs Gemini 3.8 Flash puts both models' real answers to the same prompts side by side.
Pricing
Billed per million input and output tokens, from a prepaid balance. Current rates are on pricing and the model pages in the catalog.