Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.
Use it for
- Teams evaluating coding, rag, and agents
- Workloads that can use a 1m context window
- Buyers comparing 4 tracked provider routes
Do not use it for
- Workloads where another current model has stronger sourced task evidence
- Family
- Gemini 3.1
- Released
- 2026-02-19
- Context
- 1m
- Architecture
- Decoder Only
- Knowledge cutoff
- 2025-01
- Specialization
- general
- Openness
- Proprietary
- License
- ProprietaryCommercial use: conditional
- Training
- Pretrained
Cheapest of 5 routes · GCP Vertex AI
About
Google: Gemini 3.1 Pro Preview available via OpenRouter. Pricing: $2/1M input, $12/1M output.
Gemini 3.1 Pro Preview is a proprietary model in the Gemini 3.1 family. The structured metadata tracks a 1m-token context window, multimodal input, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through Google AI Studio, GCP Vertex AI, OpenRouter, and 2 more, with the cheapest tracked route listed at $2 input and $12 output per 1M tokens. Headline tracked benchmarks include SWE-bench Pro 54.2, MMMU Pro 88.2, and SWE-bench Verified 80.6.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ D4 relevant benchmarks in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
Q/$ D3 relevant benchmarks in the decision map.
Provider price ladder
Compare all 5Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| GCP Vertex AI | $2.00 | $12.00 | Serverless |
| Google AI Studio | $2.00 | $12.00 | Serverless |
| OpenRouter | $2.00 | $12.00 | Serverless |
| Replicate API | $2.00 | $12.00 | Serverless |
Available via routers & gateways(13)
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
OpenRouter
HybridUnified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.
AIRouter
RouterCommercial LLM router that analyzes incoming requests and routes to the optimal model for cost/quality/latency via a drop-in OpenAI-compatible API, with a privacy-preserving embedding mode that avoids sending prompt content.
Helicone
GatewayObservability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.
Kong AI Gateway
GatewayMulti-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(17)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| SWE-bench Pro | 54.2 | SWE-bench Pro Public (pass@1) | https://deepmind.google/models/model-cards/gemini-3-1-pro/ |
| MMMU Pro | 88.2 | Vals.ai standardized CoT harness, 4-option, Pass@1, temp=0 | https://www.vals.ai/benchmarks/mmmu |
| SWE-bench Verified | 80.6 | SWE-bench Verified | https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-1-pro/ |
| τ-bench | 76.5 | τ-bench | https://taubench.com/ |
| MultiChallenge | 71.4 | MultiChallenge | https://labs.scale.com/leaderboard/multichallenge |
| Google-Proof Q&A | 94.3 | diamond | https://artificialanalysis.ai/leaderboards/models |
| ARC Prize / ARC Challenge | 77.1 | ARC-AGI-2 | https://artificialanalysis.ai/leaderboards/models |
| Chatbot Arena | 1493.0 | — | https://arena.ai/leaderboard |
| AIME 2025 | 95.0 | AIME 2025 (accuracy) | https://automatio.ai/models/gemini-3-1-pro |
| ARC-AGI-2 | 77.1 | ARC-AGI-2 (accuracy%) | https://benchlm.ai/benchmarks/arcAgi2 |
| BrowseComp | 85.9 | BrowseComp (accuracy) | https://deepmind.google/models/model-cards/gemini-3-1-pro/ |
| Humanity's Last Exam | 51.4 | HLE with tools (accuracy) | https://deepmind.google/models/model-cards/gemini-3-1-pro/ |
| HumanEval | 94.0 | HumanEval (pass@1) | https://automatio.ai/models/gemini-3-1-pro |
| LiveCodeBench | 91.7 | Rank 1 on pricepertoken (pass@1) | https://pricepertoken.com/leaderboards/benchmark/livecodebench |
| MCP-Atlas | 69.2 | MCP-Atlas (accuracy%) | https://llm-stats.com/benchmarks/mcp-atlas |
| Massive Multitask Language Understanding | 98.0 | MMLU (accuracy) | https://automatio.ai/models/gemini-3-1-pro |
| MMLU PRO | 91.0 | MMLU-Pro (accuracy) | https://storage.googleapis.com/deepmind-media/gemini/gemini_3-1_pro_model_evaluation.pdf |
Migration checks
No linked migration route is available for this model yet.
Rankings & picks(8)
Compare Gemini 3.1 Pro Preview with other models
- Gemini 3.1 Pro Preview vs DeepSeek V4 Pro1K
- Gemini 3.1 Pro Preview vs Grok 41K
- Gemini 3.1 Pro Preview vs Kimi K2.61K
- Gemini 3.1 Pro Preview vs Claude Opus 4.7572
- Gemini 3.1 Pro Preview vs GPT-5.5 Pro386
- Gemini 3.1 Pro Preview vs Claude Sonnet 4.5160
- Gemini 3.1 Pro Preview vs GPT-5.5156
- Gemini 3.1 Pro Preview vs Qwen3.6-Max66
Comparison and alternatives
Browse all comparisons →Show all 18 popular comparisonssorted by 7-day search impressions
Frequently asked questions
What is the context window of Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview has a context window of 1m tokens.
How much does Gemini 3.1 Pro Preview cost?
Gemini 3.1 Pro Preview pricing ranges from $2.00/1M to $2/1M input tokens depending on the provider.
When was Gemini 3.1 Pro Preview released?
Gemini 3.1 Pro Preview was released on 2026-02-19.
Which providers offer Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview is available from 5 providers: Google AI Studio, GCP Vertex AI, OpenRouter, Replicate API, Vercel AI Gateway.
What benchmarks has Gemini 3.1 Pro Preview been tested on?
Gemini 3.1 Pro Preview has been evaluated on 17 benchmarks, including SWE-bench Pro, MMMU Pro, SWE-bench Verified, τ-bench, MultiChallenge.
Cheapest of 5 routes · GCP Vertex AI