Gemini 2.5 Pro google/gemini-2.5-pro
Served by 5 providers. Cheapest: Google Gemini API (AI Studio) at $3.44 blended /1M tokens.
| Provider | Type | Input /1M | Output /1M | Cached input | Blended | Context | Notes | Source |
|---|---|---|---|---|---|---|---|---|
| Google Gemini API (AI Studio) gemini-2.5-pro |
Model labs | $1.25 | $10 | $0.125 | $3.44 | 1.05M | batch −50% >200k-token prompts: $2.50 in / $15.00 out / $0.25 cache. Cache storage $4.50/MTok-hr. Batch $0.625/$5.00. Free tier available. |
✓ src 2026-09-18 |
| Google Vertex AI (Gemini Enterprise Agent Platform) gemini-2.5-pro |
Hyperscaler AI platforms | $1.25 | $10 | $0.125 | $3.44 | — | batch −50% >200K input: $2.50 in / $15.00 out / $0.25 cached. Priority tier $2.25 in. Batch 50% per page footnote/Flex-Batch tab. |
✓ src 2026-09-18 |
| OpenRouter google/gemini-2.5-pro |
LLM routers | $1.25 | $10 | $0.125 | $3.44 | 1.05M | api modality text+image+file+audio+video->text; web_search $0.014 per web search; image $0.00000125 per input image; input_cache_write $0.375/M; internal_reasoning $10/M; audio $1.25/M; input_audio_cache $0.125/M; tier [min_prompt_tokens=200000]: prompt $2.5/M, completion $15/M, audio $2.5/M, input_audio_cache $0.25/M, input_cache_read $0.25/M; expires 2026-10-20 |
✓ src 2026-09-18 |
| Oracle OCI Generative AI | Hyperscaler AI platforms | $1.25 | $10 | — | $3.44 | — | >200K input tokens: $2.50 in / $15 out. |
✓ src src2 2026-09-18 |
| Requesty google/gemini-2.5-pro |
LLM routers | $1.25 | $10 | $0.31 | $3.44 | 1.05M | upstream route google; >200000 prompt tokens: in $2.5/M out $15/M; cache write $2.375/M; retires 1792108800; geo global; 23 other upstream routes listed (input $0.625-$1.25/M); API list price; Requesty's 5% markup on model cost (pricing page) is not included |
✓ src 2026-09-18 |
✓ from the provider's own pricing page · ◐ partly confirmed there · 2° third-party source. Router prices may exclude the router's own fees; see each router's page.