Fast Gemini model balancing multimodal reasoning, tool use, and cost
Gemini 3.5 Flash by google is offered by 36 providers on this page. Public prices are shown for 35 of them. Its official list price is $1.50 per 1M input tokens and $9.00 per 1M output tokens. The lowest paid channel is UnoRouter at $0.186 / $1.11 per 1M, about 8.9× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Artificial Analysis rates it 33.6 on the Intelligence Index. Against its lowest blended price of $0.418 per 1M, that is roughly 80 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 206 tokens per second, with 13.61s to the first token.
The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 200,000 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. 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 |
|---|---|---|---|---|---|---|---|---|
| Kenari gemini-3-5-flash | Gateway | Free | — | — | 1,048,576 | 65,536 | ||
| UnoRouter | Gateway | $0.19 | $1.11 | — | — | 1,048,576 | 65,536 | |
| Kilo Gateway | Gateway | $0.75 | $4.50 | $0.075 | $0.042 | 1,048,576 | 65,536 | |
| NanoGPT | Gateway | $1.50 | $9.00 | $0.15 | $0.083 | 1,048,576 | 65,536 | |
| NEAR AI Cloud | Gateway | $1.50 | $9.00 | $0.15 | — | 1,048,576 | 65,536 | |
| Abacus | Gateway | $1.50 | $9.00 | $0.15 | — | 1,048,576 | 65,536 | |
| 302.AI | Gateway | $1.50 | $9.00 | — | — | 1,048,576 | 65,536 | |
| OpenRouter | Gateway | $1.50 | $9.00 | $0.15 | $0.083 | 1,048,576 | 65,536 | |
| ZenMux | Gateway | $1.50 | $9.00 | $0.15 | — | 1,048,576 | 65,536 | |
| Impossibl | Gateway | $1.50 | $9.00 | $0.15 | — | 1,048,576 | 65,536 | |
| GoogleOfficial | First-party | $1.50 | $9.00 | $0.15 | — | 1,048,576 | 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 3 of 36 providers.
4 / 36 providers expose no reasoning control (reasoning_options: []).
| Provider | Audio in | Audio out |
|---|---|---|
| NEAR AI Cloud | $1.501.0× | — |
| $1.501.0× | — | |
| OrcaRouter | $3.002.0× | — |
| Ofox | $3.002.0× | — |
| Neon | $1.501.0× | — |
| Merge Gateway | $1.501.0× | — |
| GitHub Copilot | $1.501.0× | — |
| Eden AI | $3.002.0× | — |
| Tempr Gateway | $1.501.0× | — |
| OpenCode Zen | $1.501.0× | — |
| SAP AI Core | $1.501.0× | — |
| Vertex | $1.501.0× | — |
| Eden AI | $3.002.0× | — |
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.
1 more channels offer $0 (Kenari); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Terminal-Bench | harness: Terminus-2 · v2.1 | 76.2 | success rate | Source ↗ |
| SWE-Bench Pro | variant: single attempt · dataset: public | 55.1 | resolve rate | Source ↗ |
| MCP Atlas | — | 83.6 | success rate | Source ↗ |
| Toolathlon | — | 56.5 | success rate | Source ↗ |
| OSWorld-Verified | — | 78.4 | success rate | Source ↗ |
| MMMU Pro | variant: no tools | 83.6 | accuracy | Source ↗ |
| CharXiv Reasoning | variant: no tools | 84.2 | accuracy | Source ↗ |
| Humanity's Last Exam | dataset: full set, text + MM | 40.2 | accuracy | Source ↗ |
| ARC-AGI-2 | — | 72.1 | accuracy | Source ↗ |
| GDPval-AA | — | 1656 | Elo | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.