Gemini API Free Tier (Google AI Studio)
Source: https://ai.google.dev/gemini-api/docs/pricing
Description
Create account to comment on specific lines or Sign in
+ 1 Google offers completely free access to its Gemini model family via API -- no credit card required. This includes Gemini 2.5 Pro (their most capable model), Gemini 2.5 Flash, Flash-Lite, and open models like Gemma 3. All models support a 1M token context window on the free tier. The catch: rate limits are tight (especially after the December 2025 cuts), and Google may use your free-tier data for model training.
No comments on this line yet.
+ 2
No comments on this line yet.
+ 4
No comments on this line yet.
+ 5 1. Go to Google AI Studio and sign in with your Google account.
No comments on this line yet.
+ 6 2. Click Get API Key to generate a free API key -- no billing setup needed.
No comments on this line yet.
+ 7 3. Use the key with the Gemini API (REST or official SDKs for Python, Node.js, Go, Dart, etc.).
No comments on this line yet.
+ 8 4. You can test prompts directly in AI Studio's web playground before writing code.
No comments on this line yet.
+ 9 5. Rate limits apply per Google Cloud project, not per API key.
No comments on this line yet.
+ 10
No comments on this line yet.
+ 12
No comments on this line yet.
+ 13 ModelBest For
No comments on this line yet.
+ 14 Gemini 2.5 ProMost capable -- complex reasoning, coding, analysis
No comments on this line yet.
+ 15 Gemini 2.5 FlashFast + smart -- balanced speed/quality
No comments on this line yet.
+ 16 Gemini 2.5 Flash-LiteHighest free-tier limits -- lightweight tasks
No comments on this line yet.
+ 17 Gemini 2.0 FlashPrevious-gen fast model
No comments on this line yet.
+ 18 Gemini 3 Flash PreviewLatest preview model
No comments on this line yet.
+ 19 Gemini 3.1 Pro PreviewFrontier preview (limited availability)
No comments on this line yet.
+ 20 Gemma 3 / Gemma 3nOpen models, fully free
No comments on this line yet.
+ 21 Gemini EmbeddingText embeddings
No comments on this line yet.
+ 22
No comments on this line yet.
+ 24
No comments on this line yet.
+ 25 ModelRPMRPDTPM
No comments on this line yet.
+ 26 Gemini 2.5 Pro5100250,000
No comments on this line yet.
+ 27 Gemini 2.5 Flash10250250,000
No comments on this line yet.
+ 28 Gemini 2.5 Flash-Lite151,000250,000
No comments on this line yet.
+ 29 Gemini 2.0 Flash5--250,000
No comments on this line yet.
+ 30 Gemini 3 Flash PreviewFreeFreeFree
No comments on this line yet.
+ 31 Gemma 3 / Gemma 3nFreeFreeFree
No comments on this line yet.
+ 32
No comments on this line yet.
+ 33 RPM = Requests per Minute, RPD = Requests per Day, TPM = Tokens per Minute
No comments on this line yet.
+ 34
No comments on this line yet.
+ 36
No comments on this line yet.
+ 37 FeatureAvailability
No comments on this line yet.
+ 38 Context window1M tokens (all models)
No comments on this line yet.
+ 39 Google Search grounding500-5,000 RPD depending on model
No comments on this line yet.
+ 40 Google Maps grounding500-10,000 RPD depending on model
No comments on this line yet.
+ 41 Context cachingAvailable on select models
No comments on this line yet.
+ 42 Multimodal inputImages, audio, video, PDF
No comments on this line yet.
+ 43 Structured output (JSON)Supported
No comments on this line yet.
+ 44 Function callingSupported
No comments on this line yet.
+ 45
No comments on this line yet.
+ 47
No comments on this line yet.
+ 48 • December 2025 quota cuts: Google reduced free-tier limits by 50-80% in December 2025. Flash went from ~250 RPD to as low as 50 in some configs. Optimize your usage.
No comments on this line yet.
+ 49 • Data usage warning: On the free tier, Google states that your input and output data may be used to improve their products. Switch to the paid tier to opt out.
No comments on this line yet.
+ 50 • Daily quotas reset at midnight Pacific Time. Plan batch jobs accordingly.
No comments on this line yet.
+ 51 • Limits are per project, not per key. Creating multiple API keys in the same project does not increase your quota.
No comments on this line yet.
+ 52 • Flash-Lite is your best friend on the free tier -- 15 RPM and 1,000 RPD is generous enough for most prototyping and small-scale apps.
No comments on this line yet.
+ 53 • Gemini 2.5 Pro at 5 RPM / 100 RPD is tight but usable for development. Great for complex one-off tasks, not for serving traffic.
No comments on this line yet.
+ 54 • Multimodal is free -- you can process images, audio, and video with no additional cost on the free tier.
No comments on this line yet.
+ 55 • Pair with Vertex AI for higher limits: Google Cloud's Vertex AI offers Gemini with higher rate limits under the $300 Google Cloud free trial.
No comments on this line yet.
+ 56
No comments on this line yet.
+ 57 Sources:
No comments on this line yet.
+ 58 • https://ai.google.dev/gemini-api/docs/pricing
No comments on this line yet.
+ 59 • https://ai.google.dev/gemini-api/docs/rate-limits
No comments on this line yet.
+ 60 • https://aistudio.google.com/
No comments on this line yet.
+ 61 • https://www.aifreeapi.com/en/posts/gemini-api-free-tier-rate-limits
No comments on this line yet.