Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text
  3. Thinking Machines

Inkling Small

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.

  • Vision
  • Audio Input
  • Tool Calling

Added Jul 31, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.45
Output
$1.20
Cache read
$0.10
Compare provider prices

Specifications

Context window
524.3K
Max output
32.8K
Parameters
276B / 12B
Total / active

Benchmarks

Sourced from LMArena.

Arena Score

1405.4

Overall Rank

#160 / 421

Votes

37,610

Confidence Interval

1400.9 - 1409.9

Category Scores

Coding

#126 / 416

10,199 votes

1472.4

Math

#75 / 404

1,710 votes

1451.7

Longer Query

#177 / 399

17,526 votes

1400.5

Creative Writing

#219 / 419

8,145 votes

1319.0

Instruction Following

#158 / 421

13,636 votes

1396.5

Hard Prompts

#154 / 421

24,536 votes

1427.6

Additional Categories
22

Japanese

#110 / 288

616 votes

1381.9

Polish

#125 / 243

563 votes

1409.3

Industry Mathematical

#128 / 402

2,028 votes

1430.6

Industry Software And It Services

#131 / 421

14,476 votes

1458.2

Korean

#132 / 289

632 votes

1361.2

Spanish

#133 / 304

1,171 votes

1412.1

French

#135 / 301

1,242 votes

1429.9

Expert

#136 / 371

4,230 votes

1440.9

German

#147 / 320

655 votes

1387.7

Multi Turn

#147 / 419

5,840 votes

1414.4

Industry Business And Management And Financial Operations

#151 / 414

6,939 votes

1409.5

Chinese

#153 / 395

2,953 votes

1436.2

Hard Prompts English

#156 / 419

9,889 votes

1435.6

Exclude Ties

#161 / 421

27,909 votes

1389.1

Non English

#161 / 421

22,540 votes

1389.8

English

#162 / 421

15,069 votes

1416.7

Industry Life And Physical And Social Science

#165 / 419

6,193 votes

1417.4

Russian

#165 / 385

4,697 votes

1390.4

Industry Legal And Government

#185 / 393

3,226 votes

1395.4

Industry Medicine And Healthcare

#186 / 391

2,700 votes

1402.7

Industry Entertainment And Sports And Media

#195 / 419

9,817 votes

1339.0

Industry Writing And Literature And Language

#203 / 420

10,617 votes

1347.1

Published 2026-11-11 · Matched as Inkling-Small · CC BY 4.0

LMArena Dataset

Leaderboard results

BenchmarkScoreRank on NanoGPT
Epoch AI Benchmarking Hub

Epoch AI data, CC BY 4.0 · Updated Nov 15, 2026

Epoch Capabilities Index

150.8

#61 of 115

FrontierMath v2 (Tiers 1–3)

46.3%

#57 of 83

GPQA Diamond

88.5%

#50 of 119

SimpleQA Verified

19.1%

#74 of 82

FrontierMath v2 (Tier 4)

17.1%

#55 of 67

OTIS Mock AIME 2024–2025

90.0%

#58 of 121

Mystery Game Puzzles

6.0%

#76 of 77

EQ-Bench

EQ-Bench data, MIT · Updated Nov 15, 2026

Creative Writing v3

1491

#57 of 96

Filtered and ranked to models on NanoGPT.

Providers

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Auto
Auto (ZDR)
$0.45$1.20$0.10N/AN/A
Auto
Auto (Anonymized)
$0.45$1.20$0.10N/AN/A
DeepInfra
DeepInfra
FP4
US
$0.472$1.26$0.105N/AN/A
Uomi
Uomi
BF16
GLB
$0.496$1.32N/AN/AN/A
Privacy:ZDR, prompts not retainedNo training on prompts
Batch API
ProviderInputOutputCached input
Auto
Autothinkingmachines/Inkling-Small
$0.45/M$1.20/M$0.10/M

Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.

Related text models

Compare Inkling Small with similar models from the same provider or model family.

Inkling Small Thinking

thinkingmachines/Inkling-Small:thinking

The reasoning version of Thinking Machines' 276B-parameter open-weights multimodal Mixture-of-Experts model with 12B active parameters. It reasons over text and images, and is designed for agentic coding, tool use, instruction following, and long workflows with controllable thinking effort.

Inkling

thinkingmachines/inkling

The non-thinking version of Thinking Machines' 975B-parameter open-weights Mixture-of-Experts generalist with 41B active parameters. It gives faster direct answers across text, images, and audio, and is built for agentic coding, tool use, detailed instruction following, and long-context work.

Inkling Thinking

thinkingmachines/inkling:thinking

The thinking version of Thinking Machines' 975B-parameter open-weights Mixture-of-Experts generalist with 41B active parameters. It reasons natively over text, images, and audio, and is built for agentic coding, tool use, detailed instruction following, long-context work, and controllable thinking effort.

Mistral Small 3 24B (2501)

mistralai/mistral-small-24b-instruct-2501

Mistral Small 3 24B (2501) hosted by IONOS in Berlin, Germany. Zero data retention.

Mistral Small 4 119B Thinking

mistralai/mistral-small-4-119b-2603:thinking

Mistral Small 4 with reasoning enabled (reasoning_effort=high). A hybrid MoE model with deep step-by-step reasoning for complex prompts, coding, and multi-step problem solving.

Mistral Small 4 119B

mistralai/mistral-small-4-119b-2603

Mistral Small 4 is a hybrid MoE model that unifies instruct, reasoning, and coding behavior in a single multimodal model. It supports text and image input, native function calling, JSON output, and per-request reasoning effort controls.