deepseek
Gemini 3.1 Pro Preview vs DeepSeek V4 Flash Vision Exp
76.8 overall · $0.330 / 1M
Gemini 3.1 Pro Preview
google/gemini-3.1-pro-preview
reasoningtool callingaudio inputfile inputimage inputvideo inputprompt caching
Gemini 3.1 Pro Preview costs $2.00 per 1M input tokens and $12.00 per 1M output tokens with a 1.0M-token context window.
A reasoning, tool-calling model from google, released Feb 19, 2026. On LiveBench it scores 77.0 overall — #19 of 55 benchmarked models — and ranks highest in instruction following (#3).
- Input / 1M
- $2.00
- Output / 1M
- $12.00
- Context
- 1.0M
- LiveBench overall
- 77.0 · #19
Specs and pricing
| Input price USD per 1M prompt tokens | $2.00 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $12.00 |
| Blended price 3:1 input:output — #41 most expensive of 343 listed models | $4.50 |
| Cached input read Blank means not priced separately — not free | $0.200 |
| Cache write | $0.375 |
| Context window | 1,048,576 tokens |
| Max output | 65,536 tokens |
| Input modalities | audio, file, image, text, video |
| Tool calling | Yes |
| Extended reasoning | Yes |
| Knowledge cutoff | — |
| Listed | Feb 19, 2026 |
Also listed as google/gemini-3.1-pro-preview:batch ($2.25 blended)— the same model at a different price or rate limit.
Benchmarks by category
LiveBench scores out of 100, with Gemini 3.1 Pro Preview's rank among the 55 benchmarked models listed here. Run: gemini-3.1-pro-preview-high.
Language#11 of 55
85.4
$0.0571 measured per point
What Gemini 3.1 Pro Preview costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $1,310/mo |
| RAG assistant 8K in / 600 out × 100K requests | $1,600/mo |
| Coding agent 40K in / 4K out × 20K requests | $1,552/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $2,810/mo |
| Bulk classification 500 in / 20 out × 5M requests | $5,300/mo |
Compare Gemini 3.1 Pro Preview with
The benchmarked models closest to it on overall score.
anthropic
Gemini 3.1 Pro Preview vs Claude Opus 4.7
76.5 overall · $10.00 / 1M
x-ai
Gemini 3.1 Pro Preview vs SpaceXAI: Grok 4.7
77.4 overall · $2.40 / 1M
deepseek
Gemini 3.1 Pro Preview vs DeepSeek V4 Pro 0813
77.4 overall · $0.990 / 1M
anthropic
Gemini 3.1 Pro Preview vs Claude Opus 4.8
76.2 overall · $10.00 / 1M
z-ai
Gemini 3.1 Pro Preview vs GLM 5.3
76.1 overall · $0.862 / 1M
Gemini 3.1 Pro Preview FAQ
How much does Gemini 3.1 Pro Preview cost?
Gemini 3.1 Pro Preview lists at $2.00 per 1M input tokens and $12.00 per 1M output tokens, with cached input reads at $0.200 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $1,600 at list price.
What is the context window of Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview accepts up to 1,048,576 tokens of context and can return up to 65,536 output tokens per response.
Does Gemini 3.1 Pro Preview support tool calling?
Yes — Gemini 3.1 Pro Preview supports tool (function) calling and exposes extended reasoning. It accepts audio, file, image, text, video input.
How does Gemini 3.1 Pro Preview score on benchmarks?
On LiveBench release 2026-06-25 (run: gemini-3.1-pro-preview-high), Gemini 3.1 Pro Preview scores 77.0 overall, ranking #19 of 55 benchmarked models.
What is the API model ID for Gemini 3.1 Pro Preview?
On OpenRouter the model ID is "google/gemini-3.1-pro-preview". It was listed on Feb 19, 2026.
More from google
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-06-25. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.