Lean Gemini 2.5 lane for cheap multimodal traffic and quick agentsGemini 2.5 Flash-Lite by google is offered by 23 providers on this page. Public prices are shown for 21 of them. Its official list price is $0.10 per 1M input tokens and $0.40 per 1M output tokens. The lowest paid channel is LLMTR at $0.10 / $0.10 per 1M, about 1.7× 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 283 tokens per second, with 0.31s 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 1,048,576, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, Audio, Video, 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 |
|---|---|---|---|---|---|---|---|---|
| LLMTR | Gateway | $0.10 | $0.10 | — | — | 1,048,576 | 65,536 | deprecated |
| Poe | Gateway | $0.07 | $0.28 | — | — | 1,024,000 ⚠ | 64,000 | deprecated |
| Jiekou.AI | Gateway | $0.095 | $0.38 | $0.0095 | — | 1,048,576 | 65,535 | |
| VertexOfficial | Cloud | $0.10 | $0.40 | $0.01 | — | 1,048,576 | 65,536 | deprecated |
| GoogleOfficial | First-party | $0.10 | $0.40 | $0.01 | — | 1,048,576 | 65,536 | |
| CrossModel | Gateway | $0.10 | $0.40 | $0.01 | $0.10 | 1,048,576 | 65,536 | |
| Requesty gemini-2.5-flash-lite@eu | Gateway | $0.10 | $0.40 | $0.01 | $0.18 | 1,048,576 | 65,535 | |
| NanoGPT | Gateway | $0.10 | $0.40 | $0.01 | — | 1,048,576 | 65,536 | |
| NEAR AI Cloud | Gateway | $0.10 | $0.40 | $0.01 | — | 1,048,576 | 65,536 | |
| Merge Gateway | Gateway | $0.10 | $0.40 | $0.01 | — | 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.
3 / 23 providers expose no reasoning control (reasoning_options: []).
| Provider | Audio in | Audio out |
|---|---|---|
| Vertex | $0.303.0× | — |
| $0.303.0× | — | |
| NEAR AI Cloud | $0.303.0× | — |
| Merge Gateway | $0.303.0× | — |
| OpenRouter | $0.303.0× | — |
| SAP AI Core | $0.303.0× | — |
| AIHubMix | $0.303.0× | — |
| ZenMux | $0.303.0× | — |
| Ofox | $0.303.0× | — |
| OrcaRouter | $0.303.0× | — |
| Impossibl | $0.303.0× | — |
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 |
|---|---|---|---|---|
| Artificial Analysis Coding Index | — | 9.5 | index | Source ↗ |
| SciCode | — | 19.3 | percent correct | Source ↗ |
| Terminal-Bench Hard | — | 4.5 | success rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Elo from human preference matchups run by Artificial Analysis. Each arena is anchored separately, so Elo is only comparable within one arena, against the other models on that board, and the 95% confidence interval (shown as ±) indicates how much of a gap is noise. Rank is over the whole arena, including models not listed here.