NOUMENOpen app
NOUMEN

thinkingmachines · Open weights

Inkling Small

Added Jul 31, 2026Open weights

Compare models

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

Loading models…

Use in the app

The direct-answer version of Thinking Machines' 276B-parameter open-weights multimodal Mixture-of-Experts model with 12B active parameters. It accepts text and images, and is designed for coding, tool use, instruction following, and general conversational work.

  • Tools
  • Vision
  • Audio input
Input
Text, Images, Audio
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.45
Output
$1.20
Cache read
$0.10

Reference prices as published by the model provider. API example

Specifications

Context window
524.3K
Max output
32.8K
Average output (7 days)
577 tokens
Longer than 54% of 465 models

Side by side

Inkling Small 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…

Inkling SmallthinkingmachinesThis modelKimi K2.7 Code TEEMoonshotRemove
ProviderthinkingmachinesMoonshot
Discovery tierOpen weightsOpen weights
AddedJul 31, 2026Aug 15, 2026
Limits
Context window524.29KBest262.14K
Max output32.77K65.54KBest
Average output577 tokens1.1K tokens
Pricing, USD per 1M tokens
Input$0.45Best$0.95
Output$1.20Best$4.00
Cache read$0.10Best$0.19
Benchmark indexes
Intelligence Index25.725.8Best
Coding Index52.960.8Best
Capabilities
ReasoningNoYes
ToolsYesYes
VisionYesYes
Audio inputYesNo
Parallel toolsNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • Inkling Small
  • Kimi K2.7 Code TEE

Intelligence Index

  • Inkling Small25.7
  • Kimi K2.7 Code TEE25.8

Inkling Small: Better than 62% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Inkling Small: 52.9
    • Kimi K2.7 Code TEE: 60.8Top

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Inkling Small: 4.8%
    • Kimi K2.7 Code TEE: 24.5%Top

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Inkling Small: 0.6%
    • Kimi K2.7 Code TEE: 4.7%Top

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • Inkling Small: 0.0%
    • Kimi K2.7 Code TEE: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Inkling Small: 911 EloTop
    • Kimi K2.7 Code TEE: 858 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Inkling Small: 1,124 EloTop
    • Kimi K2.7 Code TEE: 1,038 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Inkling Small: 11.2%Top
    • Kimi K2.7 Code TEE: 11.2%Top

  • AA-LCRv1.1

    Reasoning across long documents

    • Inkling Small: 75.7%
    • Kimi K2.7 Code TEE: 79.3%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • Inkling Small: 7.8%
    • Kimi K2.7 Code TEE: 12.2%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Inkling Small: 33.3%
    • Kimi K2.7 Code TEE: 35.0%Top

  • GPQA Diamond

    Graduate-level science questions

    • Inkling Small: 89.5%
    • Kimi K2.7 Code TEE: 89.6%Top

  • IFBench

    Following precise output instructions

    • Inkling Small: —
    • Kimi K2.7 Code TEE: 63.1%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Inkling Small: 1.0%Top
    • Kimi K2.7 Code TEE: 1.0%Top

  • SciCode

    Scientific computing in Python

    • Inkling Small: 49.7%Top
    • Kimi K2.7 Code TEE: 47.8%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Inkling Small: —
    • Kimi K2.7 Code TEE: 44.7%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Inkling Small: —
    • Kimi K2.7 Code TEE: 90.1%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Inkling Small: 75.7%
    • Kimi K2.7 Code TEE: 79.3%Top

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

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": "thinkingmachines/Inkling-Small",
    "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="thinkingmachines/Inkling-Small",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

thinkingmachines

Other thinkingmachines models, starting with the same family.