NOUMENOpen app
NOUMEN

Google · Efficient

Gemini 3 Flash (Preview)

Added Dec 17, 2025

Compare models

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

Loading models…

Use in the app

Google's Gemini 3 Flash preview model optimized for speed while maintaining high capability. Features sub-second response times with strong multimodal understanding and reasoning. Audio input costs $1.00 per million audio tokens.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • Audio input
  • Video input
Input
Text, Images, Video, Audio
Output
Text
Reasoning effort
minimal · low · medium · high
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$0.50
Output
$3.00
Cache read
$0.05

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
65.5K
Average output (7 days)
592 tokens
Longer than 54% of 465 models

Side by side

Gemini 3 Flash (Preview) 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 Flash (Preview)GoogleThis modelGPT 5.4OpenAIRemove
ProviderGoogleOpenAI
Discovery tierEfficientFrontier
AddedDec 17, 2025Mar 5, 2026
Limits
Context window1.05M1.05MBest
Max output65.54K128KBest
Average output592 tokens409 tokens
Pricing, USD per 1M tokens
Input$0.50Best$2.50
Output$3.00Best$15.00
Cache read$0.05Best$0.25
Performance
Throughput211.2 tok/s—
Time to first token1.3 s—
Request success (24h)99.8%100.0%Best
Benchmark indexes
Intelligence Index17.918.2Best
Math Index55.7—
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputNoYes
Audio inputYesNo
Video inputYesNo
Reasoning effortminimal, low, medium, highnone, low, medium, high, xhigh

Public evaluations

Benchmarks

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

  • Gemini 3 Flash (Preview)
  • GPT 5.4

Intelligence Index

  • Gemini 3 Flash (Preview)17.9
  • GPT 5.418.2

Gemini 3 Flash (Preview): Better than 47% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • Gemini 3 Flash (Preview): 55.7
    • GPT 5.4: —

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Gemini 3 Flash (Preview): 55.3%
    • GPT 5.4: 58.3%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Gemini 3 Flash (Preview): 15.0%Top
    • GPT 5.4: 11.3%

  • GPQA Diamond

    Graduate-level science questions

    • Gemini 3 Flash (Preview): 81.2%Top
    • GPT 5.4: 74.8%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Gemini 3 Flash (Preview): 88.2%
    • GPT 5.4: —

  • IFBench

    Following precise output instructions

    • Gemini 3 Flash (Preview): 55.1%Top
    • GPT 5.4: 48.4%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Gemini 3 Flash (Preview): 79.7%
    • GPT 5.4: —

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Gemini 3 Flash (Preview): 55.7%
    • GPT 5.4: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Gemini 3 Flash (Preview): 31.8%
    • GPT 5.4: 37.9%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Gemini 3 Flash (Preview): 43.3%Top
    • GPT 5.4: 36.0%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Gemini 3 Flash (Preview): 55.3%
    • GPT 5.4: 58.3%Top

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.

Throughput
211.2 tok/s
Faster than 84% of 250 models
Time to first token
1.3 s
Quicker than 91% of 250 models
Prompt cache hits
0.0%
About $0.50 per 1M input tokens with caching
Request success (24h)
99.8%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 94.1%
  • 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": "google/gemini-3-flash-preview",
    "reasoning_effort": "medium",
    "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="google/gemini-3-flash-preview",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Google

Other Google models, starting with the same family.