NOUMENOpen app
NOUMEN

Google · Balanced

Gemini 3 Pro Image

Added Nov 18, 2025

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

Gemini 3 Pro with native image generation support. Can generate images inline from text prompts.

  • Vision
Input
Text, Images
Output
Text
Discovery tier
Balanced

Pricing

USD per 1M tokens
Input
$2.00
Output
$12.00
Cache read
$0.20

Reference prices as published by the model provider. API example

Specifications

Context window
65.5K
Max output
32.8K

Side by side

Gemini 3 Pro Image compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Gemini 3 Pro ImageGoogleThis modelOpenAI o3OpenAIRemove
ProviderGoogleOpenAI
Discovery tierBalancedBalanced
AddedNov 18, 2025Apr 16, 2025
Limits
Context window65.54K200KBest
Max output32.77K100KBest
Average output—205 tokens
Pricing, USD per 1M tokens
Input$2.00$2.00
Output$12.00$8.00Best
Cache read$0.20Best$1.00
Performance
Request success (24h)100.0%—
Benchmark indexes
Intelligence Index—20.2
Math Index—88.3
Capabilities
ReasoningNoYes
VisionYesNo
Reasoning effort—low, medium, high

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Gemini 3 Pro Image
  • OpenAI o3

Intelligence Index

  • Gemini 3 Pro Image—
  • OpenAI o320.2
3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • Gemini 3 Pro Image: —
    • OpenAI o3: 88.3

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Gemini 3 Pro Image: —
    • OpenAI o3: 74.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Gemini 3 Pro Image: —
    • OpenAI o3: 20.1%

  • GPQA Diamond

    Graduate-level science questions

    • Gemini 3 Pro Image: —
    • OpenAI o3: 82.7%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Gemini 3 Pro Image: —
    • OpenAI o3: 85.3%

  • IFBench

    Following precise output instructions

    • Gemini 3 Pro Image: —
    • OpenAI o3: 71.4%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Gemini 3 Pro Image: —
    • OpenAI o3: 80.8%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Gemini 3 Pro Image: —
    • OpenAI o3: 88.3%

  • AIME

    Competition mathematics

    • Gemini 3 Pro Image: —
    • OpenAI o3: 90.3%

  • MATH-500

    Competition math problems

    • Gemini 3 Pro Image: —
    • OpenAI o3: 99.2%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Gemini 3 Pro Image: —
    • OpenAI o3: 37.1%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Gemini 3 Pro Image: —
    • OpenAI o3: 80.7%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Gemini 3 Pro Image: —
    • OpenAI o3: 74.7%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Request success (24h)
100.0%
Reliable
Hourly request success · last 72 hoursLowest hour 66.6%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-pro-image-preview",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="gemini-3-pro-image-preview",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Google

Other Google models, starting with the same family.