← Back to the index
Google: Gemini 2.5 Pro (batch)
google/gemini-2.5-pro:batch
- Provider (catalogue)
- Weights
- Proprietary
- Context
- 1.0M
- Tokenizer
- Gemini
Price components
| Input | |
|---|---|
| Output | |
| Reasoning output | |
| Cache read | |
| Cache write (5m) | — |
| Cache write (1h) | — |
| Image input | |
| Audio input | |
| Audio output | — |
| Web search call | |
| Per request | — |
| Blended at 3:1 | $1.72 |
Conditional pricing tiers
- prompt ≥ 200K tokensinput $1.25 · output $7.50 per 1M
Conditional pricing override published by the source; not flattened into the headline rate.
Not known for this model
- Measured output tokens/sec and TTFT: no redistributable measurement source is ingested.
- Per-provider dispersion: only the catalogue-level listing is ingested so far, so provider-to-provider price and speed spread is not shown.
- Price history: no persistent store yet, so this is a point-in-time observation.
Catalogue entry last fetched just now.