Model
Gemini 3.1 Pro Preview
Reasoning-first Gemini preview for agentic coding and complex problem solving
13 providersreleased knowledge cutoff 2025-01closed weights
$2
best input /M · NanoGPT
$12
best output /M
1.05M
context window
66K
max output
Compare providers (sorted by listed input price)
| Provider | Input /M | Output /M | Cache read /M | Cache write /M | Context | Capabilities | Status | Updated |
|---|---|---|---|---|---|---|---|---|
| NanoGPT google/gemini-3.1-pro-preview | $2 | $12 | $0.2 | $0.375 | 1.05M | reasoningtoolsstructuredvision | Feb 19, 2026 | |
| Google gemini-3.1-pro-preview | $2 | $12 | $0.2 | — | 1.05M | reasoningtoolsstructuredvision | Feb 19, 2026 | |
| Impossibl google/gemini-3.1-pro-preview | $2 | $12 | $0.2 | — | 1.05M | reasoningtoolsstructuredvision | Feb 19, 2026 | |
| OpenRouter google/gemini-3.1-pro-preview | $2 | $12 | $0.2 | $0.375 | 1.05M | reasoningtoolsstructuredvision | Feb 19, 2026 | |
| Merge Gateway google/gemini-3.1-pro-preview | $2 | $12 | $0.2 | — | 1.05M | reasoningtoolsstructuredvision | Feb 19, 2026 | |
| FastRouter google/gemini-3.1-pro-preview | $2 | $12 | — | — | 1.05M | reasoningtoolsstructuredvision | Feb 19, 2026 | |
| ZenMux google/gemini-3.1-pro-preview | $2 | $12 | $0.2 | $4.50 | 1.05M | reasoningtoolsno structuredvision | Feb 19, 2026 | |
| Perplexity Agent google/gemini-3.1-pro-preview | $2 | $12 | $0.2 | — | 1.05M | reasoningtoolsno structuredvision | Feb 19, 2026 | |
| Ofox google/gemini-3.1-pro-preview | $2 | $12 | $0.2 | $4.50 | 1.05M | reasoningtoolsstructuredvision | Feb 19, 2026 | |
| Vercel AI Gateway google/gemini-3.1-pro-preview | $2 | $12 | $0.2 | — | 1M | reasoningtoolsstructuredvision | Feb 19, 2026 | |
| Eden AI google/gemini-3.1-pro-preview | $2 | $12 | $0.2 | $0.375 | 1.05M | reasoningtoolsstructuredvision | Feb 19, 2026 | |
| Kilo Gateway google/gemini-3.1-pro-preview | $2 | $12 | $0.2 | $0.375 | 1.05M | reasoningtoolsstructuredvision | Feb 19, 2026 | |
| OrcaRouter google/gemini-3.1-pro-preview | $4 | $18 | $0.2 | — | 1.05M | reasoningtoolsstructuredvision | Feb 19, 2026 |
Price badge
https://models.sutraworks.ai/badge/google/gemini-3.1-pro-preview.svgLive SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.
Benchmarks
- SWE-Bench Pro ↗(resolve rate)report ↗54.2
- Terminal-Bench ↗(success rate)report ↗70.3
- SWE-Bench Pro ↗(resolve rate)report ↗46.1
- SWE-Atlas Codebase QnA(score)report ↗13.5
- SWE-Atlas Refactoring(score)report ↗33.81
- SWE-Atlas Test Writing(score)report ↗29.84
- Artificial Analysis Coding Agent Index ↗(average pass@1)report ↗43
- SWE-Atlas Codebase QnA(pass@1)report ↗45.6
- SWE-Bench Pro ↗(pass@1)report ↗15.1
- Terminal-Bench ↗(pass@1)report ↗68.3
- GPQA Diamond ↗(accuracy)report ↗94.3
- Humanity's Last Exam ↗(accuracy)report ↗44.4
- ARC-AGI-2 ↗(accuracy)report ↗77.1
- MMMU Pro ↗(accuracy)report ↗80.5
- MCP Atlas(success rate)report ↗78.2
- OSWorld-Verified ↗(success rate)report ↗76.2
- CharXiv Reasoning(accuracy)report ↗83.3
- GDPval-AA(Elo)report ↗1314
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.