Gemini 2.5 Flash by Google AI Studio
Google’s most generous free tier - multimodal (text, vision, audio in), long context, no credit card.
Benchmarks
Numbers are copied from the linked public leaderboards for this exact model and version. The free endpoint can run a different reasoning setting or quantization than the tested one.
Quickstart
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent?key=$KEY" \
-d '{"contents":[{"parts":[{"text":"hi"}]}]}'Using this model in production?
We wire free-tier and open-weight models into production stacks: evals against your real inputs, failover, cost caps. Book a free 30-minute call.
Frequently asked
Is Gemini 2.5 Flash free?
Yes. Google AI Studio offers it as Free API tier with these limits: Free tier · existing users only, shuts down Dec 1, 2026. No credit card is required.
Can I use Gemini 2.5 Flash commercially?
Yes, commercial use is allowed. Verify the current license or terms before shipping.
How do I start using Gemini 2.5 Flash?
Get a free API key from the provider dashboard. Set the base URL to https://generativelanguage.googleapis.com and the model to gemini-2.5-flash. Google’s most generous free tier - multimodal (text, vision, audio in), long context, no credit card.
What's the catch with the free Gemini 2.5 Flash tier?
Google's Gemini API pricing page lists free-tier input and output for Gemini 2.5 Flash as free of charge, but marks free-tier usage as used to improve Google's products, and context caching isn't available on it (checked October 2026). Rate limits are set per project and shown in AI Studio. Keep client or personal data on a paid tier.
Is Gemini 2.5 Flash being shut down?
Yes. Google's deprecations page says Gemini 2.5 Flash can no longer be selected in AI Studio, API access is limited to people who already used it, and requests move to Gemini 3.5 Flash-Lite on December 1, 2026 (checked November 11, 2026). New projects should start on a current Flash model, which is still free of charge on the free tier.
Free monthly update
The monthly free-models update
What is newly free, what got rate-limited, and what to switch to. One email a month. Unsubscribe anytime.
Related free models
- GLM 4.6 (Z.ai) · Self-host free
- DeepSeek V3-0324 (DeepSeek) · Self-host free
- Gemini 2.5 Pro (Google Gemini) · Free tier · existing users only, shuts down Dec 1, 2026
- Qwen3.7 Max (Qwen) · One-time 1M tokens, 90 days (new users)
- GPT OSS 120B (Scaleway) · First 1M tokens free (shared) · then paid
- + 90 more models (NVIDIA NIM) · Prototyping only · rate limits not published