New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs
Gemini 3 Flash Preview by google is offered by 29 providers on this page. Public prices are shown for 28 of them. Its official list price is $0.50 per 1M input tokens and $3.00 per 1M output tokens. The lowest paid channel is QiHang at $0.07 / $0.43 per 1M, about 10× 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 26.3 on the Intelligence Index. Against its lowest blended price of $0.16 per 1M, that is roughly 164 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 193 tokens per second, with 6.06s to the first token.
The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 256,000 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. 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 |
|---|---|---|---|---|---|---|---|---|
| QiHang | Gateway | $0.07 tiered >200K: $0.07 | $0.43 | — | — | 1,048,576 | 65,536 | |
| Kilo Gateway | Gateway | $0.25 | $1.50 | $0.025 | $0.042 | 1,048,576 | 65,536 | |
| Perplexity Agent | Gateway | $0.50 tiered >200K: $0.50 | $3.00 | $0.05 | — | 1,048,576 | 65,536 | |
| NanoGPT | Gateway | $0.50 | $3.00 | $0.05 | — | 1,048,576 | 65,536 | |
| Databricks databricks-gemini-3-flash | Cloud | $0.50 | $3.00 | $0.05 | — | 1,048,576 | 65,536 | |
| Abacus | Gateway | $0.50 | $3.00 | $0.05 | — | 1,048,576 | 65,536 | |
| 302.AI | Gateway | $0.50 | $3.00 | — | — | 1,000,000 ⚠ | 65,536 | |
| OpenRouter | Gateway | $0.50 | $3.00 | $0.05 | $0.083 | 1,048,576 | 65,536 | |
| ZenMux | Gateway | $0.50 | $3.00 | $0.05 | $1.00 | 1,048,000 ⚠ | 64,000 | |
| GoogleOfficial | First-party | $0.50 | $3.00 | $0.05 | — | 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 4 of 29 providers.
4 / 29 providers expose no reasoning control (reasoning_options: []).
| Provider | Audio in | Audio out |
|---|---|---|
| Databricks | $1.002.0× | — |
| $1.002.0× | — | |
| OrcaRouter | $1.002.0× | — |
| Neon | $1.002.0× | — |
| Merge Gateway | $1.002.0× | — |
| Eden AI | $1.002.0× | — |
| Tempr Gateway | $1.002.0× | — |
| Vertex | $1.002.0× | — |
| Eden AI | $1.002.0× | — |
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.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Pro | dataset: public | 34.63 | resolve rate | Source ↗ |
| SWE-Atlas Codebase QnA | harness: Mini-SWE-Agent | 8.2 | score | Source ↗ |
| SWE-Atlas Refactoring | harness: Mini-SWE-Agent | 10 | score | Source ↗ |
| SWE-Atlas Test Writing | harness: Mini-SWE-Agent | 30.3 | score | 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.