Gemini 2.5 Pro
google · gemini-2-5-pro · inferred pricing
Context 2000k · Max output 8k · Released 2025-03-25 · Last verified 2026-04-28
Standard pricing (per 1M tokens)
| Tier | Input | Output |
|---|---|---|
| Standard | $1.25 | $10.00 |
| Long context (> 200k) | $2.50 | $15.00 |
Prompt caching
| Type | Price / 1M |
|---|---|
| Cache type | explicit |
| Cache read (hit) | $0.31 |
| Storage / 1M tokens / hour | $4.50 |
Want to model your real cache savings? Try the cache calculator with this model selected.
Batch API
- Input discount50%
- Output discount50%
- Stacks with cachingprovider specific
See the batch decision tool for whether this fits your workload.
Capabilities
caching extended thinking tool use vision reasoning batch
Notes & extras
- Web search: $35.00 per 1,000 searches
- Reasoning tokens: billed as output
Sources
Found a price wrong? Report it