Gemini 3.1 Pro

ChatInput: AudioInput: FileInput: ImageInput: TextReleased Feb 19, 2026

Built by Google · United States · deepmind.google

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. Building on the multimodal foundation...

How to use

model: "google/gemini-3.1-pro"

Cap quality here and save

Hard questions go to this model, easy ones drop to something cheaper. Set a savings target (0–0.8) and the router tunes itself until realized savings converge on it.

{
  "model": "celon/auto",
  "celon": {
    "anchor": "google/gemini-3.1-pro",
    "savings_target": 0.4
  }
}

Naming a model directly gets you that model — savings controls don't apply.

Context

1.0M

Max output

66K

Input $/1M

$2.00

Output $/1M

$12.00

Features

Image inputTool callingJSON

Serving providers

GoogleVertex AI

Providers

Price, latency, and uptime per provider serving this model. Celon routes each request to the fastest and cheapest of them. Click a row for regions and data policies.

Loading provider metrics…

Performance

Benchmark quality scores, and measured speed per provider.

Quality

Epoch Capabilities IndexComposite over 50+ benchmarks

154.8

GPQA DiamondPhD-level science questions

94.1%

AIMECompetition mathematics

95.6%

FrontierMathResearch-level mathematics

36.9%

Terminal-BenchAgentic terminal tasks

80.2%

SciCodeScientific code generation

58.9%

ARC-AGI-2Abstract reasoning

77.1%

SimpleQA VerifiedFactual accuracy

77.3%

HLEHumanity's Last Exam

46.4%

At each model's best reasoning effort. Benchmarks it wasn't run on are omitted.

Speed

Loading provider metrics…