Gemini 2.5 Flash-Lite
| Maker | |
|---|---|
| Family | Gemini Flash-Lite |
| Released | 2025-06-17 |
| Context | 1M |
| Max output | 65.5K |
| Open weights | Closed |
|---|---|
| Modalities | text, image, audio, video, pdf → text |
| Input / 1M | $0.10 |
| Output / 1M | $0.40 |
| Cached input / 1M | $0.01 |
| Review call | $0.0036 |
|---|---|
| Reasoning efforts | low, medium, high, xhigh, max |
| Hosts | Google Gemini, OpenRouter |
| Model id | gemini-2.5-flash-lite |
CodePanel's benchmark has not run Gemini 2.5 Flash-Lite 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 Flash-Lite line is Gemini 3.5 Flash-Lite. It caught 11% [3%–21%] of the known bugs at rank 16 of 17, with a measured review cost of $0.0059. At list price, a typical review call (26.2K tokens in and 2.4K out) costs $0.0036 on Gemini 2.5 Flash-Lite and $0.0139 on Gemini 3.5 Flash-Lite, so this model's call is 74% less than that one's.
| Host | Model id | Input / 1M | Output / 1M |
|---|---|---|---|
| Google Gemini | gemini-2.5-flash-lite | $0.10 | $0.40 |
Source: Google pricing, Oct 16, 2026
| Version | Released | Input / 1M | Output / 1M | Context | Rank | Bugs caught |
|---|---|---|---|---|---|---|
| Gemini 3.5 Flash-Lite | 2026-07-21 | $0.30 | $2.50 | 1M | #16 | 11% |
| Gemini 3.1 Flash-Lite | 2026-03-03 | $0.25 | $1.50 | 1M | – | – |
| Model | Maker | Input / 1M | Output / 1M | Review call | Context | Bugs caught |
|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | Anthropic | $0.10 | $0.50 | $0.0038 | 1M | 64% |
| GPT-6 Luna | OpenAI | $0.10 | $0.50 | $0.0038 | 1.1M | 67% |
| GPT-OSS 20B (Groq) | Groq | $0.075 | $0.30 | $0.0027 | 131.1K | – |
| GLM-5.3 Flash (Workers AI) | Z.ai | $0.15 | $0.50 | $0.0051 | 1M | 61% |
Updated Oct 23, 2026