Gemini 2.5 Pro (Batch) vs Gemini 2.5 Flash Lite
Lower and Larger mark one number at a time; they don’t rank the models. How well a model does depends on your task; see Benchmarks for measured results.
| Detail | Gemini 2.5 Pro (Batch)google/gemini-2.5-pro-batch | Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite |
|---|---|---|
| Maker | ||
| Kind | Chat | Chat |
| Input per 1M tokens | $0.65625 | $0.105 Lower |
| Cached input per 1M tokens | $0.13125 | $0.0105 |
| Cache write per 1M tokens | Same as input | Same as input |
| Output per 1M tokens | $5.25 | $0.42 Lower |
| Context window | 1,048,576 tokens | 1,048,576 tokens |
| Max output | 65,535 tokens | 65,535 tokens |
| Capabilities | Reasoning, tool use, vision, file input | Reasoning, tool use, vision, file input, web search |
| Takes | Text, image, pdf | Text, image, pdf |
| Returns | Text | Text |
| Zero data retention | Not on every provider | Not on every provider |
| No training on requests | Yes, on every provider | Yes, on every provider |
| Released | 2025-03-20 | 2025-06-17 |
Example costs
Example requests, priced at today’s rates with no cached input.
| Example request | Gemini 2.5 Pro (Batch) | Gemini 2.5 Flash Lite |
|---|---|---|
| 1,000 tokens in, 200 out | $0.001706 | $0.000189 |
| 10,000 tokens in, 1,000 out | $0.011813 | $0.00147 |
| 100,000 tokens in, 4,000 out | $0.086625 | $0.01218 |