Low-latency Gemini model for high-volume multimodal and agent workloadsGemini 3.1 Flash Lite Preview by google is offered by 11 providers on this page. Its official list price is $0.25 per 1M input tokens and $1.50 per 1M output tokens. The lowest paid channel is Kilo Gateway at $0.125 / $0.75 per 1M, about 2.0× 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, Video, Audio, and PDF. Its training knowledge cuts off at 2025-01.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Kilo Gateway | Gateway | $0.13 | $0.75 | $0.013 | $0.042 | 1,048,576 | 65,536 | |
| GoogleOfficial | First-party | $0.25 | $1.50 | $0.025 | — | 1,048,576 | 65,536 | deprecated |
| 302.AI | Gateway | $0.25 | $1.50 | — | — | 1,048,576 | 65,536 | |
| Databricks databricks-gemini-3-1-flash-lite | Cloud | $0.25 | $1.50 | $0.025 | — | 1,048,576 | 65,536 | |
| Neon gemini-3-1-flash-lite | Cloud | $0.25 | $1.50 | $0.025 | — | 1,048,576 | 65,536 | |
| OpenRouter | Gateway | $0.25 | $1.50 | $0.025 | $0.083 | 1,048,576 | 65,536 | |
| Vivgrid | Gateway | $0.25 | $1.50 | $0.025 | $1.00 | 1,048,576 | 65,536 | deprecated |
| Eden AI | Gateway | $0.25 | $1.50 | $0.025 | $0.083 | 1,048,576 | 65,536 | |
| OrcaRouter | Gateway | $0.25 | $1.50 | $0.025 | — | 1,048,576 | 65,536 | |
| Abacus | Gateway | $0.25 | $1.50 | $0.025 | $1.00 | 1,048,576 | 65,536 | deprecated |
| AI/ML API | Gateway | $0.26 | $1.59 | $0.026 | $0.088 | 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 11 providers.
1 / 11 providers expose no reasoning control (reasoning_options: []).
| Provider | Audio in | Audio out |
|---|---|---|
| $0.502.0× | — | |
| Databricks | $0.502.0× | — |
| Neon | $0.502.0× | — |
| OpenRouter | $0.502.0× | — |
| Eden AI | $0.502.0× | — |
| OrcaRouter | $0.502.0× | — |
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.
| Mode | Provider | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|
| fast | Databricks | $0.45 | $2.70 | $0.045 | — |