Fast Gemini model balancing multimodal reasoning, tool use, and cost
Gemini 3.5 Flash Lite by google is offered by 28 providers on this page. Public prices are shown for 27 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 Kilo Gateway at $0.15 / $1.25 per 1M, about 2.5× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
Artificial Analysis rates it 22.2 on the Intelligence Index, with 49.3 for coding and 14.3 for agentic tasks. Against its lowest blended price of $0.425 per 1M, that is roughly 52 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 335 tokens per second, with 9.65s to the first token. Running one task of the Artificial Analysis suite costs about $0.1235, which reflects how many tokens its reasoning consumes rather than the unit price alone.
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, Video, Audio, and PDF. Its training knowledge cuts off at 2026-03.
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 |
|---|---|---|---|---|---|---|---|---|
| Kilo Gateway | Gateway | $0.15 | $1.25 | $0.015 | $0.042 | 1,048,576 | 65,536 | |
| AIHubMix | Gateway | $0.30 | $2.50 | $0.03 | — | 1,048,576 | 65,536 | |
| NanoGPT | Gateway | $0.30 | $2.50 | $0.03 | $0.083 | 1,048,576 | 65,536 | |
| Abacus | Gateway | $0.30 | $2.50 | $0.03 | — | 1,048,576 | 65,536 | |
| 302.AI | Gateway | $0.30 | $2.50 | — | — | 1,048,576 | 65,536 | |
| OpenRouter | Gateway | $0.30 | $2.50 | $0.03 | $0.083 | 1,048,576 | 65,536 | |
| Impossibl | 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 | |
| Vercel AI Gateway | Cloud | $0.30 | $2.50 | $0.03 | — | 1,000,000 ⚠ | 65,000 | |
| OrcaRouter | Gateway | $0.30 | $2.50 | $0.03 | — | 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 2 of 28 providers.
3 / 28 providers expose no reasoning control (reasoning_options: []).
| Provider | Audio in | Audio out |
|---|---|---|
| Eden AI | $0.301.0× | — |
| Eden AI | $0.301.0× | — |
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 |
|---|---|---|---|---|
| SWE-Bench Pro | — | 54.2 | resolve rate | Source ↗ |
| Terminal-Bench | harness: Terminus 2 · v2.1 | 54 | accuracy | Source ↗ |
| MLE-Bench | — | 39.2 | average position score | Source ↗ |
| GDPval-AA | vv2 | 1140 | Elo | Source ↗ |
| OSWorld-Verified | — | 74 | success rate | Source ↗ |
| CharXiv Reasoning | variant: no tools | 74.5 | accuracy | Source ↗ |
| CharXiv Reasoning | variant: with tools | 76.5 | accuracy | Source ↗ |
| GDM-MRCR | variant: 128k average, 8-needle · vv2 | 72.2 | accuracy | Source ↗ |
| GDM-MRCR | variant: 1M pointwise, 8-needle · vv2 | 21.3 | accuracy | 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.