Gemini 2.5 Pro

ChatInput: TextInput: ImageInput: FileInput: AudioReleased Jun 17, 2025

Built by Google · United States · deepmind.google

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

How to use

model: "google/gemini-2.5-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-2.5-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

$1.25

Output $/1M

$10.00

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

146.1

GPQA DiamondPhD-level science questions

85.3%

AIMECompetition mathematics

84.2%

FrontierMathResearch-level mathematics

14.1%

SWE-bench VerifiedReal GitHub issue resolution

57.6%

Terminal-BenchAgentic terminal tasks

32.6%

SciCodeScientific code generation

42.8%

ARC-AGI-2Abstract reasoning

4.9%

SimpleQA VerifiedFactual accuracy

56.0%

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

Speed

Loading provider metrics…