# Gemini 1.5 Pro API Rate Limits, Pricing & Performance (July 2026)

- Tool: AI API Limits & Performance Matrix
- Last updated: July 2026

## TL;DR

Gemini 1.5 Pro has been shut down and is no longer available via API. API calls using 'gemini-1.5-pro' will fail. Migrate to Gemini 2.5 Pro (gemini-2.5-pro): same 1M+ context window, improved reasoning, $1.25/$10.00 per MTok (≤200K tokens) — paid-only since April 1, 2026. Below are the current rate limits and pricing for Gemini 2.5 Pro, the direct successor.

## Frequently asked questions

### Is Gemini 1.5 Pro still available?

No. Gemini 1.5 Pro has been shut down and is no longer available via the Google AI API. API calls using the 'gemini-1.5-pro' model string will fail with a model-not-found error. Migrate to 'gemini-2.5-pro' immediately.

### How do I migrate from Gemini 1.5 Pro to 2.5 Pro?

The minimum change is updating the model string in your API calls from 'gemini-1.5-pro' to 'gemini-2.5-pro'. Then: (1) add a Google Cloud billing account if you haven't (2.5 Pro is paid-only since April 1, 2026), (2) review your prompt lengths against the 200K long-context surcharge threshold, and (3) test for any behavioral differences. Most migrations are straightforward model-string replacements.

### What are the rate limits for Gemini 2.5 Pro?

Google does not publish stable RPM or TPM numbers for Gemini 2.5 Pro. Your active quota is project-specific and shown in AI Studio dashboard. To increase limits, go to Google Cloud Console → IAM & Admin → Quotas → Generative Language API and request an increase (typically 1–5 business days).

### How much does Gemini 2.5 Pro cost?

As of July 2, 2026 (when prices were raised): $1.25 per million input tokens and $10.00 per million output tokens for requests under 200K tokens. Requests over 200K tokens cost $2.50/$15.00 per MTok — and this surcharge applies to the ENTIRE prompt, not just the tokens above the threshold. Context cache reads cost ~$0.125/MTok. A 50% batch discount is available.

### Is Gemini 2.5 Pro free?

No. Gemini 2.5 Pro has been paid-only since April 1, 2026. There is no free tier. If you need a free tier for prototyping, use Gemini 2.5 Flash instead (approximately 1,500 requests/day free, though exact limits are not published by Google).

### What is the 200K token surcharge for Gemini 2.5 Pro?

When any single request has more than 200K tokens, the input price doubles from $1.25 to $2.50/MTok and the output price rises from $10.00 to $15.00/MTok — and this applies to the WHOLE prompt, not just the tokens above 200K. Crossing the threshold by a single token nearly doubles the cost of that request. Hard-limit prompt length below 200K where possible.

### How can RapidDev help with Gemini API migration?

RapidDev specializes in API quota engineering and model migrations. If you're moving a production system from Gemini 1.5 Pro to 2.5 Pro and need help with cost modeling, prompt optimization, or context caching architecture, reach out at rapidevelopers.com/contact for a free scoping call.

---

Source: https://www.rapidevelopers.com/ai-api-limits-performance-matrix/gemini-1-5-pro
© RapidDev — https://www.rapidevelopers.com/ai-api-limits-performance-matrix/gemini-1-5-pro