Gemini 2.5 Pro
| Maker | |
|---|---|
| Family | Gemini Pro |
| Released | 2025-03-25 |
| Context | 1M |
| Max output | 65.5K |
| Open weights | Closed |
|---|---|
| Modalities | text, image, audio, video, pdf → text |
| Input / 1M | $1.25 |
| Output / 1M | $10.00 |
| Cached input / 1M | $0.125 |
| Above 200K in | $2.50 / $15.00 |
|---|---|
| Review call | $0.0569 |
| Reasoning efforts | low, medium, high, xhigh, max |
| Hosts | Google Gemini, OpenRouter |
| Model id | gemini-2.5-pro |
CodePanel's benchmark has not run Gemini 2.5 Pro as a pull-request reviewer yet, so this page has no recall, false-alarm or measured-cost figures for it. The methodology explains how ranked models are scored.
The newest ranked model in the Gemini Pro line is Gemini 3.1 Pro. It caught 67% [54%–80%] of the known bugs at rank 2 of 17, with a measured review cost of $0.2499. At list price, a typical review call (26.2K tokens in and 2.4K out) costs $0.0569 on Gemini 2.5 Pro and $0.0814 on Gemini 3.1 Pro, so this model's call is 30% less than that one's.
| Host | Model id | Input / 1M | Output / 1M |
|---|---|---|---|
| Google Gemini | gemini-2.5-pro | $1.25 | $10.00 |
Source: Google pricing, Oct 16, 2026
| Version | Released | Input / 1M | Output / 1M | Context | Rank | Bugs caught |
|---|---|---|---|---|---|---|
| Gemini 3.1 Pro | 2026-02-19 | $2.00 | $12.00 | 1M | #2 | 67% |
| Model | Maker | Input / 1M | Output / 1M | Review call | Context | Bugs caught |
|---|---|---|---|---|---|---|
| GPT-5 | OpenAI | $1.25 | $10.00 | $0.0569 | 400K | – |
| Mistral Medium 3.5 | Mistral | $1.50 | $7.50 | $0.0574 | 256K | – |
| Qwen3.7 Max | Qwen | $1.475 | $4.425 | $0.0494 | 1M | – |
| GLM-5.3 (Workers AI) | Z.ai | $1.40 | $4.40 | $0.0473 | 1M | 61% |
Updated Oct 23, 2026