NOUMENOpen app
NOUMEN

Google · Efficient

Gemini 3.1 Flash Lite

Added Mar 3, 2026

Compare models

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

Loading models…

Use in the app

Google's Gemini 3.1 Flash Lite. Optimized for high-volume, cost-efficient reasoning and multimodal workloads.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • PDF input
  • 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
$0.25
Output
$1.50
Cache read
$0.025
Cache write
$0.0833

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
65.5K
Average output (7 days)
669 tokens
Longer than 59% of 465 models

Side by side

Gemini 3.1 Flash Lite 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 3.1 Flash LiteGoogleThis modelDeepSeek V3.2DeepSeekRemove
ProviderGoogleDeepSeek
Discovery tierEfficientOpen weights
AddedMar 3, 2026Dec 1, 2025
Limits
Context window1.05MBest163K
Max output65.54K65.54K
Average output669 tokens408 tokens
Pricing, USD per 1M tokens
Input$0.25$0.21Best
Output$1.50$0.31Best
Cache read$0.025$0.0216Best
Cache write$0.0833—
Performance
Throughput—50.2 tok/s
Time to first token—2.6 s
Request success (24h)100.0%Best99.6%
Benchmark indexes
Intelligence Index15.616.0Best
Coding Index34.7—
Math Index—59.0
Capabilities
ReasoningYesNo
ToolsYesYes
VisionYesNo
Structured outputYesYes
PDF inputYesYes
Audio inputYesNo
Video inputYesNo
Reasoning effortminimal, low, medium, high—

Public evaluations

Benchmarks

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

  • Gemini 3.1 Flash Lite
  • DeepSeek V3.2

Intelligence Index

  • Gemini 3.1 Flash Lite15.6
  • DeepSeek V3.216.0

Gemini 3.1 Flash Lite: Better than 39% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Gemini 3.1 Flash Lite: 34.7
    • DeepSeek V3.2: —

  • Math Index

    Composite of the math evaluations

    • Gemini 3.1 Flash Lite: —
    • DeepSeek V3.2: 59.0

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Gemini 3.1 Flash Lite: 6.8%
    • DeepSeek V3.2: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Gemini 3.1 Flash Lite: 0.5%
    • DeepSeek V3.2: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Gemini 3.1 Flash Lite: 207 Elo
    • DeepSeek V3.2: —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Gemini 3.1 Flash Lite: 430 Elo
    • DeepSeek V3.2: —

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Gemini 3.1 Flash Lite: 7.8%
    • DeepSeek V3.2: —

  • AA-LCRv1.1

    Reasoning across long documents

    • Gemini 3.1 Flash Lite: 74.3%Top
    • DeepSeek V3.2: 45.7%

  • MLCR-AA

    Long-context reasoning over medical records

    • Gemini 3.1 Flash Lite: 5.0%
    • DeepSeek V3.2: —

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Gemini 3.1 Flash Lite: 17.2%Top
    • DeepSeek V3.2: 11.2%

  • GPQA Diamond

    Graduate-level science questions

    • Gemini 3.1 Flash Lite: 82.2%Top
    • DeepSeek V3.2: 75.1%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Gemini 3.1 Flash Lite: —
    • DeepSeek V3.2: 83.7%

  • IFBench

    Following precise output instructions

    • Gemini 3.1 Flash Lite: 77.2%Top
    • DeepSeek V3.2: 49.0%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Gemini 3.1 Flash Lite: 0.5%
    • DeepSeek V3.2: —

  • SciCode

    Scientific computing in Python

    • Gemini 3.1 Flash Lite: 43.4%
    • DeepSeek V3.2: —

  • LiveCodeBench

    Recent competitive programming problems

    • Gemini 3.1 Flash Lite: —
    • DeepSeek V3.2: 59.3%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Gemini 3.1 Flash Lite: —
    • DeepSeek V3.2: 59.0%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Gemini 3.1 Flash Lite: 24.2%
    • DeepSeek V3.2: 32.6%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Gemini 3.1 Flash Lite: 31.3%
    • DeepSeek V3.2: 78.9%Top

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Gemini 3.1 Flash Lite: 74.3%Top
    • DeepSeek V3.2: 45.7%

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.

Prompt cache hits
41.0%
About $0.16 per 1M input tokens with caching
Request success (24h)
100.0%
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 100.0%
  • 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": "google/gemini-3.1-flash-lite",
    "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-3.1-flash-lite",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Google

Other Google models, starting with the same family.