NOUMENOpen app
NOUMEN

Google · Efficient

Gemini 2.5 Flash Preview (09/2025) – Thinking

Added Sep 25, 2025

Compare models

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

Loading models…

Use in the app

Same checkpoint with thinking enabled by default for deeper reasoning and stepwise analysis on complex tasks. Routed to Gemini 2.5 Flash Thinking (stable).

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

Pricing

USD per 1M tokens
Input
$0.30
Output
$2.50
Cache read
$0.03

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
65.5K

Side by side

Gemini 2.5 Flash Preview (09/2025) – Thinking 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 2.5 Flash Preview (09/2025) – ThinkingGoogleThis modelGemini 3.5 Flash ThinkingGoogleRemove
ProviderGoogleGoogle
Discovery tierEfficientEfficient
AddedSep 25, 2025May 19, 2026
Limits
Context window1.05M1.05M
Max output65.54K65.54K
Average output—1.7K tokens
Pricing, USD per 1M tokens
Input$0.30Best$1.50
Output$2.50Best$9.00
Cache read$0.03Best$0.15
Cache write—$0.0833
Performance
Throughput—255.7 tok/s
Time to first token—10.3 s
Request success (24h)99.3%Best89.1%
Benchmark indexes
Intelligence Index15.532.6Best
Coding Index—70.1
Math Index78.3—
Capabilities
ReasoningYesYes
ToolsYesNo
VisionYesYes
Structured outputYesNo
PDF inputYesNo
Audio inputYesYes
Video inputNoYes
Reasoning effortlow, medium, highminimal, low, medium, high

Public evaluations

Benchmarks

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

  • Gemini 2.5 Flash Preview (09/2025) – Thinking
  • Gemini 3.5 Flash Thinking

Intelligence Index

  • Gemini 2.5 Flash Preview (09/2025) – Thinking15.5
  • Gemini 3.5 Flash Thinking32.6

Gemini 2.5 Flash Preview (09/2025) – Thinking: Better than 39% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: —
    • Gemini 3.5 Flash Thinking: 70.1

  • Math Index

    Composite of the math evaluations

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: 78.3
    • Gemini 3.5 Flash Thinking: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: —
    • Gemini 3.5 Flash Thinking: 42.1%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: —
    • Gemini 3.5 Flash Thinking: 13.5%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: —
    • Gemini 3.5 Flash Thinking: 874 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: —
    • Gemini 3.5 Flash Thinking: 1,202 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: —
    • Gemini 3.5 Flash Thinking: 19.8%

  • AA-LCRv1.1

    Reasoning across long documents

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: 71.0%
    • Gemini 3.5 Flash Thinking: 73.3%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: —
    • Gemini 3.5 Flash Thinking: 10.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: 13.8%
    • Gemini 3.5 Flash Thinking: 42.7%Top

  • GPQA Diamond

    Graduate-level science questions

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: 79.3%
    • Gemini 3.5 Flash Thinking: 92.2%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: 84.2%
    • Gemini 3.5 Flash Thinking: —

  • IFBench

    Following precise output instructions

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: 52.3%
    • Gemini 3.5 Flash Thinking: 76.3%Top

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: —
    • Gemini 3.5 Flash Thinking: 6.6%

  • SciCode

    Scientific computing in Python

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: —
    • Gemini 3.5 Flash Thinking: 53.9%

  • LiveCodeBench

    Recent competitive programming problems

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: 71.3%
    • Gemini 3.5 Flash Thinking: —

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: 78.3%
    • Gemini 3.5 Flash Thinking: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: 16.7%
    • Gemini 3.5 Flash Thinking: 40.9%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: 45.6%
    • Gemini 3.5 Flash Thinking: 95.3%Top

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Gemini 2.5 Flash Preview (09/2025) – Thinking: 71.0%
    • Gemini 3.5 Flash Thinking: 73.3%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.

Request success (24h)
99.3%
Reliable
Hourly request success · last 72 hoursLowest hour 99.0%
  • 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-2.5-flash-preview-09-2025-thinking",
    "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="gemini-2.5-flash-preview-09-2025-thinking",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Google

Other Google models, starting with the same family.