High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoningGemini 3.7 Flash by google is offered by 34 providers on this page. Its official list price is $0.75 per 1M input tokens and $3.75 per 1M output tokens. The lowest paid channel is Kenari at $0.343 / $1.71 per 1M, about 2.2× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
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, PDF, Audio, and Video. Its training knowledge cuts off at 2026-03.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Kenari gemini-3-7-flash | Gateway | $0.34 | $1.71 | $0.034 | $0.017 | 1,048,576 | 65,536 | deprecated |
| VertexOfficial | Cloud | $0.75 | $3.75 | $0.075 | — | 1,048,576 | 65,536 | |
| GoogleOfficial | First-party | $0.75 | $3.75 | $0.075 | — | 1,048,576 | 65,536 | |
| Perplexity Agent | Gateway | $0.75 | $3.75 | $0.075 | — | 1,048,576 | 65,536 | |
| CrossModel | Gateway | $0.75 | $3.75 | $0.075 | $0.75 | 1,048,576 | 65,536 | |
| LLM Gateway | Gateway | $0.75 | $3.75 | $0.075 | $0.083 | 1,048,576 | 65,536 | |
| 302.AI | Gateway | $0.75 | $3.75 | $0.075 | — | 1,048,576 | 65,536 | |
| Requesty | Gateway | $0.75 | $3.75 | $0.075 | — | 1,048,576 | 65,535 | |
| NanoGPT | Gateway | $0.75 | $3.75 | $0.075 | $0.042 | 1,048,576 | 65,536 | |
| DevPass (LLM Gateway) | Gateway | $0.75 | $3.75 | $0.075 | $0.083 | 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 1 of 34 providers.
3 / 34 providers expose no reasoning control (reasoning_options: []).
| Provider | Audio in | Audio out |
|---|---|---|
| Vertex | $0.751.0× | — |
| $0.751.0× | — | |
| OpenRouter | $0.751.0× | — |
| AIHubMix | $0.751.0× | — |
| Ofox | $0.751.0× | — |
| OpenCode | $0.751.0× | — |
| Eden AI | $1.501.0× | — |
| Eden AI | $1.501.0× | — |
| Eden AI | $1.651.0× | — |
| Eden AI | $1.651.0× | — |
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 |
|---|---|---|---|---|
| FrontierCode | v1.1 Main | 43.6 | score | Source ↗ |
| DeepSWE | v1.1 | 65.3 | resolve rate | Source ↗ |
| Terminal-Bench | v2.1 | 85.8 | accuracy | Source ↗ |
| AutomationBench | dataset: private set | 30.4 | accuracy | Source ↗ |
| GDP.pdf | — | 34 | accuracy | Source ↗ |
| GDM-MRCR | variant: 128k average, 8-needle · vv2 | 97 | accuracy | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.