Skip to content

Thinking Machines · Chat

Inkling FP4

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 is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems.
llminfo IQ
126.9
Max context
1M
Listings
38

Evidence and sources

🤗 thinkingmachines/Inklingllminfo IQ 126.9, ranked among chat models. From 215 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 101.9, 95% interval 96–107. From 16 benchmark families across 8 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 (27.9). Costs more per task than its benchmark results predict. From 49 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 resultsChatty (58 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. By effort: default 58 · none 38.Median 48,499 output tokens per task at default effort.How the Yap score worksReleased 14 Jul 2026Maker HQ: US (source)
All rankings: #1 in Hacker News discussions this week #82 on OpenRouter this month #125 on NanoGPT recently #207 on OpenRouter today #211 on OpenRouter this weekAll rankings: #1 in Hacker News discussions this week #82 on OpenRouter this month #125 on NanoGPT recently #207 on OpenRouter today #211 on OpenRouter this weekSources: LMArena data, Together AI data, LiteLLM data, Models.dev data, AI/ML API data, Hugging FacePrimary data from LMArena from Together AI: name from LiteLLM: deprecation date from Models.dev: weights availability from AI/ML API: primary mode, description from Hugging Face: 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. 4 of the 9 peers that say either way have 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 9 maker's prices; 1 market median price.

Input & output

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

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingAudio input

Listings

 Thinking Machinesthinkingmachines/InklingSource: Models.dev data66K$1.87cache read $0.374$4.68
 Flowdotthinkingmachines/inkling:free · freeSource: FlowDot data1M$0.00$0.00
 Eden AIInference by DeepInfradeepinfra/thinkingmachines/InklingSource: Models.dev data524K$0.95cache read $0.16$4.05
 Hugging FaceInference by DeepInfrathinkingmachines/InklingSource: Hugging Face Inference Providers data524K$0.95$4.05
 DeepInfradeepinfra/thinkingmachines/Inkling · fp8Sources: LiteLLM data, Models.dev data524K$0.95cache read $0.16$4.05
 Fastrouterthinkingmachines/inklingSource: FastRouter data524K$1.00cache read $0.17$4.05
 Kilothinkingmachines/inklingSources: Kilo AI Gateway data, Models.dev data524K$1.00cache read $0.17$4.05
 NanoGPTthinkingmachines/inklingSources: Models.dev data, NanoGPT1M$1.00cache read $0.17$4.05
 Nous Portalthinkingmachines/inklingSource: Nous Portal Inference Gateway data524K$1.00cache read $0.17$4.05
 OpenRouterthinkingmachines/inklingSources: Models.dev data, OpenRouter data docs524K$1.00cache read $0.17$4.05
Show all 36 listings

Showing 10 of 36: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Abacus, Aimlapi, Baseten, Commandcode, Databricks, Fireworks AI, Hyper, Impossibl, Llmtr, Merge Gateway, Microsoft Azure, Modal, Requesty, Together AI, Vercel.

2 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 ELO52 related benchmarks · 52 results
Source: LMArena data · Nov 2026
BenchmarkScore
Arena ELO
Chinese
Creative Writing
English
Show 48 more benchmarksHide 48 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 - Japanese
Text Factuality - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
Text Factuality - Polish
Text Factuality - Russian
Text Factuality - Spanish
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

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
Source: OpenRouter benchmark exports
15 Jul 2026 version · 90-day results
Across 3 providers lowest 67.3% median 68.2% highest 69%OpenRouter's automatic routing 66%
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
Tau3 Banking5 related benchmarks · 5 results
Tau3 Banking
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
tau3-bench v1 banking-knowledge pass^1
Source: Sierra tau-bench Leaderboard data docs · Jul 2026
submission-inkling_sierra_2026-08-04, usersim-gpt-5.2, effort-max, retrieval-alltools
tau3-bench v1 banking-knowledge pass^2
Source: Sierra tau-bench Leaderboard data docs · Jul 2026
submission-inkling_sierra_2026-08-04, usersim-gpt-5.2, effort-max, retrieval-alltools
tau3-bench v1 banking-knowledge pass^3
Source: Sierra tau-bench Leaderboard data docs · Jul 2026
submission-inkling_sierra_2026-08-04, usersim-gpt-5.2, effort-max, retrieval-alltools
tau3-bench v1 banking-knowledge pass^4
Source: Sierra tau-bench Leaderboard data docs · Jul 2026
submission-inkling_sierra_2026-08-04, usersim-gpt-5.2, effort-max, retrieval-alltools
Source: WeirdML v3 data
config: inkling-deepinfra-xhigh-opencode, agent: opencode, harness: opencode@1.19.0, effort: xhigh
config: inkling-together-xhigh-opencode, agent: opencode, harness: opencode@1.18.30, effort: xhigh

Coding

Arena ELOSource: LMArena data · Nov 2026

General

Multilingual

Reasoning

Math

Science

GPQA Diamond5 results
Source: OpenRouter benchmark exports
15 Jul 2026 version · 90-day results
Across 3 providers lowest 81.9% median 84.4% highest 84.5%OpenRouter's automatic routing 83.4%
Show results from 3 providers and OpenRouter's automatic routingHide results from 3 providers and OpenRouter's automatic routing
  • DeepInfra
  • Together
  • OpenRouter's automatic routing
  • BaseTen

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

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

Knowledge

Other

Vals17 related benchmarks · 19 results
EMB
Source: Vals AI
CorpFin v2
Source: Vals AI
Show 13 more resultsHide 13 results
LegalBench
Source: Vals AI
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: Data by LLM Stats · 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) · LMArena, CC BY 4.0 (licence) · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · Steel.dev Agent Leaderboards, MIT (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (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) · Sierra Research tau2-bench leaderboard submissions (github.com/sierra-research/tau2-bench), MIT (licence) · WeirdML v3 by Håvard Tveit Ihle (Norwegian Defence Research Establishment). API costs supported by Epoch AI, METR and NDRE.

Around the web

Also known as: accounts/fireworks/models/inkling, azure_ai/fw-inkling, baseten/thinkingmachines/inkling, databricks/databricks-inkling, deepinfra/thinkingmachines/inkling, fireworks_ai/accounts/fireworks/models/inkling, thinkingmachines/inkling, thinkingmachines/inkling-nvfp4, thinkingmachines/inkling:free, thinkingmachines/inkling:thinking, together_ai/thinkingmachines/inkling

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