Nadhebe
guides

Gemini API Pricing, Free Tier & Rate Limits (2026 Developer Breakdown)

Detailed breakdown of Google Gemini API pricing rates, free tier RPM/TPM limits, model token costs, and pay-as-you-go billing.

Nadhebe Editorial Team Nadhebe Editorial Team
· · 2 min read
GPU Lab Verified
Clean minimalist technical meter gauge illustration of Gemini API pricing
On this page

Understanding the Gemini API pricing structure and rate limit quotas is critical for building cost-effective production applications. Google offers both a Free Tier in Google AI Studio for prototyping and a Pay-As-You-Go Tier for production workloads.


Free Tier vs Pay-As-You-Go Model Overview

FeatureFree Tier (AI Studio)Pay-As-You-Go Tier
Price$0.00Pay per 1M tokens
Data PrivacyPrompts used to train modelsPrompts NOT used to train models
Gemini 1.5 Flash RPM15 RPM1,000 RPM
Gemini 1.5 Pro RPM2 RPM360 RPM
Max Context Window1,000,000 Tokens2,000,000 Tokens

Token Pricing Breakdown (Pay-As-You-Go)

Google charges based on input tokens (prompt text/images/audio) and output tokens generated by the model.

1. Gemini 1.5 & 2.0 Flash (High Speed / Low Cost)

  • Input Tokens (prompts < 128k): $0.075 per 1 million tokens
  • Input Tokens (prompts > 128k): $0.15 per 1 million tokens
  • Output Tokens: $0.30 per 1 million tokens
  • Context Caching: $0.01875 per 1M tokens/hour

2. Gemini 1.5 Pro (Deep Reasoning / Complex Code)

  • Input Tokens (prompts < 128k): $1.25 per 1 million tokens
  • Input Tokens (prompts > 128k): $2.50 per 1 million tokens
  • Output Tokens: $5.00 per 1 million tokens

Understanding Gemini API Rate Limits

Rate limits are measured across three metrics:

  1. RPM (Requests Per Minute): Number of individual API calls per 60 seconds.
  2. TPM (Tokens Per Minute): Total combined input + output tokens processed per minute.
  3. RPD (Requests Per Day): Hard cap on daily API invocations (1,500 RPD on Free Tier).
429 Quota Exceeded -> Solution: Implement exponential backoff or upgrade to Pay-As-You-Go billing.

FAQ

Does Google train on Free Tier API data?

Yes. On the Free Tier in Google AI Studio, input prompts and output responses may be reviewed by human annotators to improve Google models. If handling sensitive PII data, use the Pay-As-You-Go Tier.

How do I increase my Gemini API rate limits?

To increase RPM and TPM limits beyond the free quotas, add a credit card in Google Cloud Console under Billing -> Linked AI Studio Project.

Nadhebe Editorial Team

Nadhebe Editorial Team

The collective editorial desk, technical writers, and hardware validation engineers at Nadhebe. All publications undergo multi-stage peer review and physical GPU lab validation.

Includes Free AI Starter Kit

The Weekly AI Engineering Briefing

Join AI engineers building with Claude, MCP, Gemini, and open-source models. Received by developers, researchers, and technical founders.