Fast Gemini workhorse for multimodal apps where latency and price matterGemini 2.5 Flash by google is offered by 33 providers on this page. Public prices are shown for 31 of them. Its official list price is $0.30 per 1M input tokens and $2.50 per 1M output tokens. The lowest paid channel is QiHang at $0.09 / $0.71 per 1M, about 3.5× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
Median output speed is 216 tokens per second, with 17.85s to the first token.
The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 1,000,000 to 1,065,535, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, Video, Audio, and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-01.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| QiHang | Gateway | $0.09 tiered >200K: $0.09 | $0.71 | — | — | 1,048,576 | 65,536 | |
| Poe | Gateway | $0.21 | $1.80 | $0.021 | — | 1,065,535 ⚠ | 65,535 | deprecated |
| Jiekou.AI | Gateway | $0.29 | $2.38 | $0.029 | — | 1,048,576 | 65,535 | |
| Cortecs | Gateway | $0.30 | $2.49 | $0.029 | $0.097 | 1,048,576 | 65,535 | |
| AIHubMix | Gateway | $0.30 | $2.50 | $0.03 | — | 1,048,576 | 65,536 | |
| GoogleOfficial | First-party | $0.30 | $2.50 | $0.03 | — | 1,048,576 | 65,536 | |
| VertexOfficial | Cloud | $0.30 | $2.50 | $0.03 | — | 1,048,576 | 65,536 | deprecated |
| CrossModel | Gateway | $0.30 | $2.50 | $0.03 | $0.30 | 1,048,576 | 65,536 | |
| 302.AI gemini-2.5-flash-nothink | Gateway | $0.30 | $2.50 | — | — | 1,000,000 ⚠ | 65,536 | |
| 302.AI | Gateway | $0.30 | $2.50 | — | — | 1,000,000 ⚠ | 65,536 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 1 of 33 providers.
5 / 33 providers expose no reasoning control (reasoning_options: []).
| Provider | Audio in | Audio out |
|---|---|---|
| AIHubMix | $1.003.3× | — |
| $1.003.3× | — | |
| Vertex | $1.003.3× | — |
| Databricks | $1.003.3× | — |
| NEAR AI Cloud | $1.003.3× | — |
| Merge Gateway | $1.003.3× | — |
| OpenRouter | $1.003.3× | — |
| SAP AI Core | $1.003.3× | — |
| ZenMux | $1.003.3× | — |
| Ofox | $1.003.3× | — |
| FastRouter | $1.003.3× | — |
| OrcaRouter | $1.003.3× | — |
| Impossibl | $1.003.3× | — |
Audio tokens are priced on a separate scale from text tokens, so these are not comparable with the text prices above. The multiplier compares each price with the same provider's text price for the same direction.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Aider Polyglot | — | 55.1 | percent correct | Source ↗ |
| Artificial Analysis Coding Index | — | 22.2 | index | Source ↗ |
| SciCode | — | 39.4 | percent correct | Source ↗ |
| Terminal-Bench Hard | — | 13.6 | success rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.