Skip to content

Thinking Machines · Chat

Inkling Small

Thinking Machines 🇺🇸ChatInkling familyOpen weights. One of its sources says the weights are publicly available.The maker lists this model as deprecated (16 Oct 2026).
From Aiml API's listing:
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family.
llminfo IQ
127.4
Maker's price
$0.795 blended / 1M
Max context
1M
Listings
28

Evidence and sources

🤗 thinkingmachines/Inkling-Smallllminfo IQ 127.4, ranked among chat models. From 169 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 107.0, 95% interval 101–114. From 12 benchmark families across 5 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (45.5). Costs more per task than its benchmark results predict. From 35 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsTerse (42 ±9). Generates fewer tokens than models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate.Median 20,104 output tokens per task with reasoning off.How the Yap score worksReleased 30 Jul 2026Maker HQ: US (source)
All rankings: #106 on OpenRouter this month #255 on OpenRouter this week #368 on OpenRouter today #450 on NanoGPT recentlySources: LMArena data, DeepInfra data, LiteLLM data, Models.dev data, AI/ML API data, llminfo researchPrimary data from LMArena from DeepInfra: name from LiteLLM: deprecation date from Models.dev: weights availability from AI/ML API: primary mode, description from llminfo research: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 1 of the 8 peers that say either way has open weights.

Trade-offs

Deprecated by its maker

The maker has already deprecated this model (16 Oct 2026).

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 10 maker's prices.

Input & output

as stated by the model's providers
Text
Images
Audio
Files
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt caching

Listings

 Thinking Machinesthinkingmachines/Inkling-SmallSource: Models.dev data66K$0.58cache read $0.116$1.44
 Flowdotthinkingmachines/inkling-small:free · freeSource: FlowDot data1M$0.00$0.00
 Nous Portalthinkingmachines/inkling-small:batch · batchSource: Nous Portal Inference Gateway data524K$0.36cache read $0.08$0.96
 OpenRouterInference by DeepInfrathinkingmachines/inkling-small:batch · batch, fp8 · fp8Source: OpenRouter data docs524K$0.36cache read $0.08$0.96
 Eden AIInference by DeepInfradeepinfra/thinkingmachines/Inkling-SmallSource: Models.dev data524K$0.45cache read $0.10$1.20
 Fastrouterthinkingmachines/inkling-smallSource: FastRouter data524K$0.45cache read $0.10$1.20
 Hugging FaceInference by DeepInfrathinkingmachines/Inkling-SmallSource: Hugging Face Inference Providers data524K$0.45$1.20
 Kilothinkingmachines/inkling-smallSources: Kilo AI Gateway data, Models.dev data524K$0.45cache read $0.10$1.20
 NanoGPTthinkingmachines/Inkling-SmallSources: Models.dev data, NanoGPT524K$0.45cache read $0.10$1.20
 Vercelthinkingmachines/inkling-smallSources: Models.dev data, Vercel AI Gateway data1M$0.45cache read $0.10$1.20
Show all 25 listings

Showing 10 of 25: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Aimlapi, Arcee, Baseten, Commandcode, DeepInfra, Llmtr.

3 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Human preference

Arena ELO58 related benchmarks · 58 results
Source: LMArena data · Nov 2026
BenchmarkScore
Arena ELO
Chinese
Creative Writing
English
Show 54 more benchmarksHide 54 benchmarks
BenchmarkScore
Exclude Ties
Expert
French
German
Hard Prompts
Hard Prompts English
Industry Business and Management and Financial Operations
Industry Entertainment and Sports and Media
Industry Life and Physical and Social Science
Industry Mathematical
Industry Medicine and Healthcare
Industry Software and It Services
Industry Writing and Literature and Language
Japanese
Korean
Longer Query
Multi Turn
Non English
Polish
Russian
Spanish
Style-Controlled
Text Factuality
Text Factuality - Chinese
Text Factuality - Creative Writing
Text Factuality - English
Text Factuality - Exclude Ties
Text Factuality - Expert
Text Factuality - French
Text Factuality - German
Text Factuality - Hard Prompts
Text Factuality - Hard Prompts English
Text Factuality - Industry Business and Management and Financial Operations
Text Factuality - Industry Entertainment and Sports and Media
Text Factuality - Industry Life and Physical and Social Science
Text Factuality - Industry Mathematical
Text Factuality - Industry Medicine and Healthcare
Text Factuality - Industry Software and It Services
Text Factuality - Industry Writing and Literature and Language
Text Factuality - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
Text Factuality - Russian
Text Factuality - Spanish
Vision
Vision - Chinese
Vision - Creative Writing Vision
Vision - Diagram
Vision - English
Vision - Homework
Vision - Humor
Vision Style-Controlled

Long context

GDM-MRCRv2: 8 needle7 related benchmarks · 42 results
Source: Context Arena data · Aug 2026
Benchmarkminimallowmediumhighmaxnot stated
GDM-MRCRv2: 8 needle
8k
16k
32k
Show 3 more benchmarksHide 3 benchmarks
Benchmarkminimallowmediumhighmaxnot stated
64k
128k
256k

Agentic

Arena AgentSource: LMArena data
GDPval-AASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MCP AtlasSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Source: OpenRouter benchmark exports
30 Jul 2026 version · 90-day results
Across 2 providers lowest 60.5% median 61.4% highest 62.3%OpenRouter's automatic routing 61.2%
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
  • Together
  • OpenRouter's automatic routing
  • DeepInfra

Coding

Arena ELOSource: LMArena data · Nov 2026
ValsSource: Vals AI

Reasoning

ARC-AGI3 related benchmarks · 14 results
ARC-AGI
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
ARC-AGI 2
Source: Epoch AI Benchmarking Hub data
Reasoning effort
v2
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Multilingual

Math

Science

CritPTSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond5 results
Source: OpenRouter benchmark exports
30 Jul 2026 version · 90-day results
Across 3 providers lowest 86.8% median 86.9% highest 87.2%OpenRouter's automatic routing 86.3%
Show results from 3 providers and OpenRouter's automatic routingHide results from 3 providers and OpenRouter's automatic routing
  • BaseTen
  • Together
  • DeepInfra
  • OpenRouter's automatic routing

General

Instruction following

IFBenchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Factuality

Speech

MMAUSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Vision

CharXiv-RSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MMMU-ProSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Knowledge

OCR

Other

Artificial Analysis9 related benchmarks · 9 results
Briefcase
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Show 3 more resultsHide 3 results
Vals16 related benchmarks · 18 results
EMB
Source: Vals AI
CorpFin v2
Source: Vals AI
EMB v1.1
Source: Vals AI
Show 12 more resultsHide 12 results
MedCode
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated
MedScribe
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated

Data credits: Hugging Face official benchmark leaderboards; licence varies by benchmark · SEA-HELM leaderboard, AI Singapore (AI Products team), National University of Singapore. Published aggregate scores; results licence not stated (SEA-HELM code is MIT). · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Data by LLM Stats · LMArena, CC BY 4.0 (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence)

Also known as: baseten/thinkingmachines/inkling-small, deepinfra/thinkingmachines/inkling-small, thinkingmachines/inkling-small, thinkingmachines/inkling-small:batch, thinkingmachines/inkling-small:free, thinkingmachines/inkling-small:thinking

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works