Google

Gemini 3.1 Pro

Gemini 3.1 Pro is a Gemini 3 model from Google, released in 2026-04. It costs $2 / $12 per 1M, has a 2M-token context window, and is best for long-context, video-understanding, maps. Last verified 2026-04-19.

Try Gemini 3.1 Pro Docs Take the picker quiz

Spec sheet

Pricing

Input
$2 / 1M
Output
$12 / 1M
Cached input
$0.5 / 1M
Batch discount
50%
Free tier
No

Context & speed

Context window
2M tokens
Max output
66k tokens
Throughput
~95 tok/s
Time to first token
~550 ms
Speed tier
balanced

Capabilities

Tool use
Yes
Structured output
Yes
Prompt caching
Yes
Extended thinking
Yes
Vision input
Yes
Audio in / out
Yes
Fine-tuning
Yes

Deployment

Open weights
No
On-prem
No
HIPAA eligible
Yes
Zero retention
Yes
Regions
us, eu, apac

Estimated monthly cost

Assumes typical token shape: 2k input, 600 output per call. Prompt caching is excluded from these figures.

10k calls/mo
$112.00
per month
100k calls/mo
$1.1k
per month
1M calls/mo
$11k
per month

When to use Gemini 3.1 Pro

Sweet spot

  • long context
  • video understanding
  • maps
  • multilingual
  • vision
  • rag

Known trade-offs

  • $4/$18 tier above 200K input tokens
  • paid-only since Apr 2026

Best use cases

Best LLM for Maps

Google knowledge graph + Maps-adjacent training data makes this the default

Best LLM for Long documents (100k+ tokens)

2M context window — the largest from any frontier lab

Best LLM for RAG

2M context + top long-context retrieval benchmarks

Best LLM for Vision

Highest vision benchmark; also handles video natively

Best LLM for Translation

Strong general multilingual; 2M context for doc-length work

Works with

Google AI SDKVertex AIVercel AI SDKLangChainLlamaIndexOpenRouter

Compare Gemini 3.1 Pro to other models

vs Claude Sonnet 4.6vs GPT-5.4vs GPT Realtimevs Grok 4.20vs Claude Haiku 4.5vs GPT-5.4 Mini

FAQ — Gemini 3.1 Pro

How much does Gemini 3.1 Pro cost?

Gemini 3.1 Pro costs $2 / $12 per 1M tokens on the Google API. Cached input reads cost $0.5 per 1M, cutting the input bill by roughly 75% on repeat system prompts. The batch API offers a 50% discount for async workloads.

What is the context window of Gemini 3.1 Pro?

Gemini 3.1 Pro has a 2M-token context window with up to 66k tokens of output. That's enough for entire codebases, long transcripts, or multi-document RAG.

Does Gemini 3.1 Pro have a free tier?

No — Paid-only since 2026-04-01 (previously had free tier via AI Studio).

Is Gemini 3.1 Pro HIPAA / EU / on-prem friendly?

Gemini 3.1 Pro is HIPAA-eligible, available in EU regions, and is API-only. Zero data retention is available for enterprise customers.

What is Gemini 3.1 Pro best for?

Gemini 3.1 Pro is best for long context, video understanding, maps, multilingual. Trade-offs to be aware of: $4/$18 tier above 200K input tokens; paid-only since Apr 2026.

Which tools and SDKs work with Gemini 3.1 Pro?

Gemini 3.1 Pro integrates with Google AI SDK, Vertex AI, Vercel AI SDK, LangChain, LlamaIndex, OpenRouter. Most major AI frameworks support it either natively or through OpenAI-compatible endpoints.