Context
1M
Max output
66K
Serving providers
4
Cheapest input
$2.00 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: ARC Prize and Artificial AnalysisSpeed & latency
Output speed
118 t/s
tokens / second
Time to first token
29.48s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |
|---|---|---|---|---|
| Aa Analyst Agent | 0.4 | default | — | |
| AA-Briefcase | 0% | — | — | |
| APEX Agents | 32% | default | — | |
| ARC-AGI-2 | 77% | default | $0.962 | |
| Automation Bench | 0.4 | default | — | |
| CritPt | 18% | default | — | |
| GDPval | 965.1 | default | — | |
| GPQA Diamond | 94% | default | — | |
| Harvey Lab | 0.6 | default | — | |
| Humanity's Last Exam | 47% | default | — | |
| IFBench | 77% | default | — | |
| IT-Bench SRE | 30% | default | — | |
| Long-Context Reasoning | 79% | default | — | |
| Mlcr Overall | 0.2 | default | — | |
| MMMU-Pro | 82% | default | — | |
| Omniscience | 31.9 | default | — | |
| Omniscience Accuracy | 0.5 | default | — | |
| Omniscience Non Hallucination | 0.5 | default | — | |
| SciCode | 59% | default | — | |
| TerminalBench Hard | 54% | default | — | |
| TerminalBench v2.1 | 74% | default | — | |
| τ-bench Banking | 21% | default | — | |
| τ²-bench | 96% | default | — |
Pricing detail
cost beyond the standard rate · source: models.devLong context (>200K)
$5.00 / $22.50
input / output · per 1M
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Vertex AICheapest | $2.00 | $12.00 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Vertex AICheapest | $2.00 | $12.00 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| GoogleCheapest | $2.00 | $12.00 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| OpenRouterCheapest | $2.00 | $12.00 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Cost calculator
estimate your monthly spend on this model$1,360
estimated / month
Model IDs
copy the exact identifier for your platformvertex_ai/gemini-3.1-pro-previewgemini-3.1-pro-previewgemini/gemini-3.1-pro-previewgoogle/gemini-3.1-pro-preview
Frequently asked questions
Gemini 3.1 Pro Preview pricing, context and availabilityHow much does Gemini 3.1 Pro Preview cost?
Gemini 3.1 Pro Preview costs $2.00 per 1M input tokens and $12.00 per 1M output tokens at its cheapest provider via Vertex AI.
What is the context window of Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview accepts up to 1M tokens of context and can return up to 66K output tokens.
Which providers serve Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview is available from 4 serving providers, each with its own pricing and model ID. Vertex AI is currently the cheapest.
What can Gemini 3.1 Pro Preview do?
Gemini 3.1 Pro Preview supports image input (vision), tool use, reasoning, audio input, prompt caching, structured output and web search.
Other Google models
compare pricing across the Google lineupPopular comparisons
head-to-head pages featuring Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview vs Claude Fable 5side-by-side pricing & benchmarks Gemini 3.1 Pro Preview vs Claude Opus 4.8side-by-side pricing & benchmarks Gemini 3.1 Pro Preview vs Claude Sonnet 5side-by-side pricing & benchmarks
Gemini 3.1 Pro Preview vs DeepSeek V4 Pro 0423side-by-side pricing & benchmarks
Gemini 3.1 Pro Preview vs Gemini 3.5 Flashside-by-side pricing & benchmarks Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI