Reasoning-first Gemini preview for agentic coding and complex problem solvingGemini 3.1 Pro Preview by google is offered by 46 providers on this page. Public prices are shown for 45 of them. Its official list price is $2.00 per 1M input tokens and $12.00 per 1M output tokens. The lowest paid channel is Infer by Flow7 at $1.18 / $5.30 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.
Median output speed is 137 tokens per second, with 23.66s to the first token.
The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 199,999 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 |
|---|---|---|---|---|---|---|---|---|
| Infer by Flow7 infer/gemini-3.1-pro-preview:low-cost | Gateway | $1.18 | $5.30 | $0.12 | $1.33 | 199,999 ⚠ | 65,536 | |
| Kenari gemini-3-1-pro | Gateway | $1.20 | $7.14 | $0.12 | $0.22 | 1,048,576 | 65,536 | |
| VertexOfficial | Cloud | $2.00 tiered >200K: $4.00 | $12.00 | $0.20 | — | 1,048,576 | 65,536 | beta |
| GoogleOfficial gemini-pro-latest | First-party | $2.00 tiered >200K: $4.00 | $12.00 | $0.20 | — | 1,048,576 | 65,536 | |
| GoogleOfficial | First-party | $2.00 tiered >200K: $4.00 | $12.00 | $0.20 | — | 1,048,576 | 65,536 | |
| Perplexity Agent | Gateway | $2.00 tiered >200K: $4.00 | $12.00 | $0.20 | — | 1,048,576 | 65,536 | |
| CrossModel | Gateway | $2.00 tiered >200K: $4.00 | $12.00 | $0.20 | $2.00 | 1,048,576 | 65,536 | |
| LLM Gateway | Gateway | $2.00 tiered >200K: $4.00 | $12.00 | $0.20 | — | 1,048,576 | 65,536 | |
| LLM Gateway | Gateway | $2.00 tiered >200K: $4.00 | $12.00 | $0.20 | — | 1,048,576 | 65,536 | |
| LLM Gateway | Gateway | $2.00 tiered >200K: $4.00 | $12.00 | $0.20 | — | 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 46 providers.
6 / 46 providers expose no reasoning control (reasoning_options: []).
| Provider | Audio in | Audio out |
|---|---|---|
| Databricks | $2.001.0× | — |
| OpenRouter | $2.001.0× | — |
| Eden AI | $2.001.0× | — |
| Eden AI | $2.001.0× | — |
| Ofox | $2.001.0× | — |
| OrcaRouter | $2.001.0× | — |
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 | $3.60 | $21.60 | $0.36 | — |
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Pro | — | 54.2 | resolve rate | Source ↗ |
| Terminal-Bench | harness: Terminus-2 · v2.1 | 70.3 | success rate | Source ↗ |
| SWE-Bench Pro | dataset: public | 46.1 | resolve rate | Source ↗ |
| SWE-Atlas Codebase QnA | harness: Mini-SWE-Agent | 13.5 | score | Source ↗ |
| SWE-Atlas Refactoring | harness: Gemini CLI | 33.81 | score | Source ↗ |
| SWE-Atlas Test Writing | harness: Mini-SWE-Agent | 29.84 | score | Source ↗ |
| Artificial Analysis Coding Agent Index | harness: Gemini CLI · variant: high | 43 | average pass@1 | Source ↗ |
| SWE-Atlas Codebase QnA | harness: Gemini CLI · variant: high | 45.6 | pass@1 | Source ↗ |
| SWE-Bench Pro | harness: Gemini CLI · variant: high · dataset: hard-aa | 15.1 | pass@1 | Source ↗ |
| Terminal-Bench | harness: Gemini CLI · variant: high · v2.1 | 68.3 | pass@1 | Source ↗ |
| GPQA Diamond | — | 94.3 | accuracy | Source ↗ |
| Humanity's Last Exam | dataset: full set, text + MM | 44.4 | accuracy | Source ↗ |
| ARC-AGI-2 | — | 77.1 | accuracy | Source ↗ |
| MMMU Pro | variant: no tools | 80.5 | accuracy | Source ↗ |
| MCP Atlas | — | 78.2 | success rate | Source ↗ |
| OSWorld-Verified | — | 76.2 | success rate | Source ↗ |
| CharXiv Reasoning | variant: no tools | 83.3 | accuracy | Source ↗ |
| GDPval-AA | — | 1314 | 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 scale (percent correct, points or an index), so rows are not comparable with one another.