Gemini 2.5 Flash google/gemini-2.5-flash
Served by 5 providers. Cheapest: Requesty at $0.425 blended /1M tokens. The most expensive listing costs 2.0× as much for the same model.
| Provider | Type | Input /1M | Output /1M | Cached input | Blended | Context | Notes | Source |
|---|---|---|---|---|---|---|---|---|
| Requesty google/gemini-2.5-flash:flex |
LLM routers | $0.15 | $1.25 | $0.03 | $0.425 | 1.05M | upstream route google; retires 1792108800; geo global; 23 other upstream routes listed (input $0.3-$0.3/M); API list price; Requesty's 5% markup on model cost (pricing page) is not included |
✓ src 2026-09-18 |
| Google Gemini API (AI Studio) gemini-2.5-flash |
Model labs | $0.30 | $2.50 | $0.03 | $0.85 | 1.05M | batch −50% Audio input $1.00 (cache $0.10). Batch $0.15/$1.25. Free tier available. |
✓ src 2026-09-18 |
| Google Vertex AI (Gemini Enterprise Agent Platform) gemini-2.5-flash |
Hyperscaler AI platforms | $0.30 | $2.50 | $0.03 | $0.85 | — | batch −50% Audio input $1.00 (cached $0.10). |
✓ src 2026-09-18 |
| OpenRouter google/gemini-2.5-flash |
LLM routers | $0.30 | $2.50 | $0.03 | $0.85 | 1.05M | api modality text+image+file+audio+video->text; web_search $0.014 per web search; image $0.0000003 per input image; input_cache_write $0.0833333333333333/M; internal_reasoning $2.5/M; audio $1/M; input_audio_cache $0.1/M; expires 2026-10-20 |
✓ src 2026-09-18 |
| Oracle OCI Generative AI | Hyperscaler AI platforms | $0.30 | $2.50 | — | $0.85 | — | Audio input $1.00/M. |
✓ src src2 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.