Gemini 3.1 Flash Lite retirement date: May 7, 2027
gemini-3.1-flash-lite can be shut down as early as May 7, 2027.
- Provider
- Google (Gemini API)
- Model IDs affected
gemini-3.1-flash-lite- Shutdown date
- May 7, 2027 earliest possible
- Replacement
- gemini-3.5-flash-lite
- Platforms
- Dates apply to the Gemini API and are the earliest possible shutdown dates Google publishes. If you use Gemini through another platform, check that platform's own schedule.
- Source
- Official Google (Gemini API) deprecations page (data last changed 2026-11-02, re-checked daily)
Gemini 3.1 Flash Lite vs Gemini 3.5 Flash Lite: price and limits
| Gemini 3.1 Flash Lite | Gemini 3.5 Flash Lite | Change | |
|---|---|---|---|
| Context window (tokens) | 1,048,576 | 1,048,576 | 0% |
| Max output (tokens) | 65,536 | 65,536 | 0% |
| Input, $ per 1M tokens | $0.25 | $0.30 | +20% |
| Output, $ per 1M tokens | $1.50 | $2.50 | +67% |
| Cache read, $ per 1M tokens | $0.03 | $0.03 | +20% |
Prices and limits from models.dev (checked 2026-11-02). Confirm on the official pricing page. Compare the cost for your traffic in the old vs new model calculator.
Migrating from Gemini 3.1 Flash Lite to Gemini 3.5 Flash Lite
Not yet reviewed. We haven't written model-specific migration notes for Gemini 3.1 Flash Lite yet. Start with the provider's official guidance and the replacement's model page, and use this general checklist:
- Search your code, config and environment variables for
gemini-3.1-flash-lite. - Re-run your evaluation set against gemini-3.5-flash-lite before switching traffic.
- Recount tokens with the new model's tokenizer and re-check
max_tokens, context fit and cost. - Check tool calling, structured output and stop sequences on your real prompts.
- Dates apply to the Gemini API and are the earliest possible shutdown dates Google publishes. If you use Gemini through another platform, check that platform's own schedule.
Check your code before May 7
All model retirements · All Google (Gemini API) deprecations
FAQ
When will Gemini 3.1 Flash Lite be retired?
Gemini 3.1 Flash Lite (gemini-3.1-flash-lite) shuts down on the Gemini API on May 7, 2027, according to the official Gemini API deprecations page. Google lists this as the earliest possible shutdown date; the exact date is announced later.
What should I use instead of gemini-3.1-flash-lite?
The recommended replacement is gemini-3.5-flash-lite.
What happens to gemini-3.1-flash-lite requests after the shutdown date?
After a model is retired, API requests to it return an error. Move traffic to the replacement and test it on your own prompts before the date.
Does this date apply to Amazon Bedrock, Vertex AI or Azure?
Dates apply to the Gemini API and are the earliest possible shutdown dates Google publishes. If you use Gemini through another platform, check that platform’s own schedule.