Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows.
- Input / output price
- $2.00 / $12.00 per 1M
- Context
- 1M tokens
- Released
- Aug 6, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
5 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Concentrate concentrate/gemini-3.1-pro-preview | $2.00/M | $12.00/M |
Google Gemini AI google_gemini_ai/gemini-3.1-pro-preview | $2.00/M | $12.00/M |
Inference.net inference_net/gemini-3.1-pro-preview | $2.00/M | $12.00/M |
Perplexity perplexity/gemini-3.1-pro-preview | $2.00/M | $12.00/M |
OpenRouter openrouter/gemini-3.1-pro-preview | $2.00/M | $12.00/M |
Is a provider down? Perplexity status, OpenRouter status
Pricing
Averaged across 5 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $2.00 per 1M
- Average output
- $12.00 per 1M
- Average cache read
- $0.20 per 1M
- Average cache write
- $0.13 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better394tokens/sacross providers
Time to first token
Lower is better14sacross providers
Response latency
Lower is better7.6sacross providers
Benchmarks
The Respan Index plus 38 published scores from 16 sources, each linked to where it was published.
43.6/ 100
Respan Index#61 of 176
- 61Gemini 3.1 Pro Preview43.6
- 60Mistral Large 444.1
- 62GLM-5.243.4
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench CodingLiveBench | 76.5% | LiveBench | Oct 5, 2026 |
| SWE-bench VerifiedEpoch AI | 75.6% | Epoch AI | Oct 5, 2026 |
| WeirdMLHåvard Tveit Ihle | 72.1% | Håvard Tveit Ihle | Oct 5, 2026 |
| SWE-Bench ProOpenAI | 54.2% | OpenAI | Jul 9, 2026 |
| GSO Opt@1GSO | 21.6% | GSO | Mar 9, 2026 |
| DeepSWE v1.1Datacurve | 11.7% | Datacurve | Oct 5, 2026 |
| MirrorCodeEpoch AI | 8.9% | Epoch AI | Oct 5, 2026 |
| Terminal-Bench 4.0Vals AI | 2.5% | Vals AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Toolathlon-VerifiedHKUST | 61.1% | HKUST | Jul 1, 2026 |
| BALROGBALROG | 57% | BALROG | Feb 25, 2026 |
| LiveBench Agentic CodingLiveBench | 44.1% | LiveBench | Oct 5, 2026 |
| APEX-AgentsMercor | 35.1% | Mercor | Oct 28, 2026 |
| tau2-bench Banking KnowledgeSierra | 26% | Sierra | May 5, 2026 |
| Vending-Bench 2Andon Labs | 3774.25 · #45 of 68 | Andon Labs | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondEpoch AI | 94.4% | Epoch AI | Oct 5, 2026 |
| GPQA DiamondOpenAI | 94.3% | OpenAI | Jul 9, 2026 |
| LiveBench ReasoningLiveBench | 84% | LiveBench | Oct 5, 2026 |
| SimpleBenchSimpleBench | 79.6% | SimpleBench | Feb 17, 2026 |
| LiveBench Data AnalysisLiveBench | 78.5% | LiveBench | Oct 5, 2026 |
| ARC-AGI-2Google | 77.1% | Feb 19, 2026 | |
| Chess PuzzlesEpoch AI | 51% | Epoch AI | Oct 28, 2026 |
| Mystery Game PuzzlesEpoch AI | 34% | Epoch AI | Oct 5, 2026 |
| EBR-benchEpoch AI | 14.3% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| AIME 2026MathArena | 98.3% | MathArena | Sep 17, 2026 |
| OTIS Mock AIME 2024-2025Epoch AI | 95.6% | Epoch AI | Oct 5, 2026 |
| LiveBench MathematicsLiveBench | 91% | LiveBench | Oct 5, 2026 |
| FrontierMath Tiers 1-3 v2Epoch AI | 59.6% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tier 4 v2Epoch AI | 26.8% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench LanguageLiveBench | 85.4% | LiveBench | Oct 5, 2026 |
| LiveBench Instruction FollowingLiveBench | 79.1% | LiveBench | Oct 5, 2026 |
| SimpleQA VerifiedEpoch AI | 73.5% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Furniture AssemblyEpoch AI | 26.7% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1487 Elo · #20 of 191 | LMArena | Nov 19, 2026 |
| LMArena WebDevLMArena | 1446 Elo · #73 of 124 | LMArena | Nov 19, 2026 |
| LMArena VisionLMArena | 1280 Elo · #22 of 91 | LMArena | Nov 19, 2026 |
| LMArena AgentLMArena | -0.0569 · #53 of 68 | LMArena | Nov 18, 2026 |
How Gemini compares: Claude vs Gemini, Gemini vs GPT, Gemini vs Grok
Compare Gemini 3.1 Pro Preview: Gemini 3.1 Pro Preview vs Gemini 3 Pro Preview, Gemini 3.1 Pro Preview vs Claude Sonnet 5.5, Gemini 3.1 Pro Preview vs GPT-5.6 Luna, Gemini 3.1 Pro Preview vs GPT-6.1 Sol, Gemini 3.1 Pro Preview vs Gemini 4 Neon, Gemini 3.1 Pro Preview vs Gemini 4 Carbon
Apps
Use Gemini 3.1 Pro Preview in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Gemini 3.1 Pro Preview FAQ
Short answers, built from the data on this page.
Gemini 3.1 Pro Preview is a model from Google Gemini AI, released on Aug 6, 2026. Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows.
On the Respan gateway, Gemini 3.1 Pro Preview costs $2.00 per 1M input tokens and $12.00 per 1M output tokens on every provider, after gateway discounts.
Gemini 3.1 Pro Preview is available through 5 providers: Concentrate, Google Gemini AI, Inference.net, Perplexity, and OpenRouter.
Gemini 3.1 Pro Preview accepts up to 1M tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "google_gemini_ai/gemini-3.1-pro-preview". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Gemini 3.1 Pro Preview scores 43.6 out of 100 on the Respan Index v1.1, ranking #61 of 176 models. By category: Coding 14.7, Agents 53.4, Reasoning 45.8, Knowledge & language 72.5, and Human preference 52.5. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
Gemini 3.1 Pro Preview has 38 published benchmark scores, including LiveBench Coding 76.5%, Toolathlon-Verified 61.1%, and GPQA Diamond 94.4%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.