NOUMENOpen app
NOUMEN

inclusionai · Open weights

Ling 3.1 Flash

Added Sep 30, 2026Open weights

Compare models

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

Loading models…

Use in the app

Ling 3.1 Flash is inclusionAI's hybrid reasoning model for coding, tool use, planning, and long-context agent workflows. It has 560B total parameters with 25B active parameters per token. Thinking is enabled by default and can be turned off in settings.

  • Reasoning
  • Tools
  • Structured output
Input
Text
Output
Text
Reasoning effort
none · low · medium · high
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.075
Output
$0.22
Cache read
$0.015

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
32.8K
Average output (7 days)
7.8K tokens
Longer than 99% of 465 models

Side by side

Ling 3.1 Flash 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…

Ling 3.1 FlashinclusionaiThis modelGLM 5.3 Flash TEEZ.aiRemove
ProviderinclusionaiZ.ai
Discovery tierOpen weightsOpen weights
AddedSep 30, 2026Aug 28, 2026
Limits
Context window262.14K1.05MBest
Max output32.77K131.07KBest
Average output7.8K tokens845 tokens
Pricing, USD per 1M tokens
Input$0.075Best$0.15
Output$0.22Best$0.50
Cache read$0.015Best$0.03
Performance
Throughput86.1 tok/sBest75.4 tok/s
Time to first token2.7 sBest3.8 s
Request success (24h)100.0%Best99.9%
Benchmark indexes
Intelligence Index41.141.8Best
Coding Index—71.5
Capabilities
ReasoningYesYes
ToolsYesYes
VisionNoYes
Structured outputYesYes
Parallel toolsNoYes
Reasoning effortnone, low, medium, highlow, high, max

Public evaluations

Benchmarks

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

  • Ling 3.1 Flash
  • GLM 5.3 Flash TEE

Intelligence Index

  • Ling 3.1 Flash41.1
  • GLM 5.3 Flash TEE41.8

Ling 3.1 Flash: Better than 86% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Ling 3.1 Flash: —
    • GLM 5.3 Flash TEE: 71.5

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Ling 3.1 Flash: 61.7%Top
    • GLM 5.3 Flash TEE: 60.4%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Ling 3.1 Flash: 23.6%
    • GLM 5.3 Flash TEE: 25.4%Top

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • Ling 3.1 Flash: —
    • GLM 5.3 Flash TEE: 0.8%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Ling 3.1 Flash: 1,397 Elo
    • GLM 5.3 Flash TEE: 1,452 EloTop

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Ling 3.1 Flash: 1,617 Elo
    • GLM 5.3 Flash TEE: 1,642 EloTop

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Ling 3.1 Flash: 10.0%
    • GLM 5.3 Flash TEE: 15.4%Top

  • AA-LCRv1.1

    Reasoning across long documents

    • Ling 3.1 Flash: 83.0%Top
    • GLM 5.3 Flash TEE: 80.0%

  • MLCR-AA

    Long-context reasoning over medical records

    • Ling 3.1 Flash: 12.2%Top
    • GLM 5.3 Flash TEE: 11.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Ling 3.1 Flash: 39.4%
    • GLM 5.3 Flash TEE: 39.9%Top

  • GPQA Diamond

    Graduate-level science questions

    • Ling 3.1 Flash: —
    • GLM 5.3 Flash TEE: 91.2%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Ling 3.1 Flash: 33.3%Top
    • GLM 5.3 Flash TEE: 32.8%

  • SciCode

    Scientific computing in Python

    • Ling 3.1 Flash: 54.1%Top
    • GLM 5.3 Flash TEE: 51.6%

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Ling 3.1 Flash: 83.0%Top
    • GLM 5.3 Flash TEE: 80.0%

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
86.1 tok/s
Faster than 57% of 250 models
Time to first token
2.7 s
Quicker than 63% of 250 models
Prompt cache hits
94.4%
About $0.0184 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 88.3%
  • 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": "inclusionai/ling-3.1-flash",
    "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="inclusionai/ling-3.1-flash",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

inclusionai

Other inclusionai models, starting with the same family.