Skip to content
AI Atlas
ModelActiveOpen weightsIdentity probable

Inkling

Thinking Machines

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,...

Open in Graph
data quality60

Updated 1 h ago · first seen 11 Sept 2026

model_01M294WVTGRQG13Q8WGWXSATQB

Overview

Identity

Canonical model
Yesidentity confidence: mediumOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
Official checkpoints
official_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
Artifacts
1 quantization0 official · 1 third-partySeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
2
API aliases
inklingthinkingmachines/inklingIdentifiers under which providers and evaluators refer to this model.
Folded evaluation variants
1Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.

Openness

Open weights— weights downloadable; 7 dimensions unknown.

Weights downloadable under a permissive or Creative Commons licence allowing commercial use; code or data may be missing.

  • Weights

    Yes

  • Inference code

    —

  • Training code

    —

  • Training data

    —

  • Dataset

    —

  • Commercial use

    —

  • Redistribution

    —

  • Derivatives

    —

dimensions marked null are unknown, not false

Key facts

Release date

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Architecture

Hugging Face repo

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Capabilities

Modalities

Modalities
audioimagetext
Input
audioimagetext
Output
text

Capabilities

  • Tool calling

    Yes

    OpenRouter public model & pricing listing · T2

  • Structured output

    Yes

    OpenRouter public model & pricing listing · T2

  • Reasoning

    Yes

    OpenRouter public model & pricing listing · T2

  • Vision

    Yes

    OpenRouter public model & pricing listing · T2

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:OpenRouter public model & pricing listingT2observed 10 h agomedium

Max output

Source:OpenRouter public model & pricing listingT2observed 1 h agomedium

Benchmarks22

Compare with another model →

Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric

Benchmark results grouped by comparability group
Benchmark · groupBest scoreTrustConfigurationResultsvs leaderEvaluatedSource
Terminal-Benchagentic · accuracy · variant=v2.1 · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisvariantv2.1reasoningonconditions differ across rows → partially comparable2non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
Terminal-Benchagentic · accuracy · variant=v4.0 · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisvariantv4.0reasoningonconditions differ across rows → partially comparable2non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
LiveBench Agentic Codingcoding · average score · variant=Agentic CodingOfficial boardvariantAgentic Codingreasoning_effortxhighrelease2026-06-25conditions differ across rows → partially comparable1−27.9 ptvs DeepSeek-V4.1-Flash25 Jun 2026livebench.aiT2
LiveBench Codingcoding · average score · variant=CodingOfficial boardvariantCodingreasoning_effortxhighrelease2026-06-25conditions differ across rows → partially comparable1−15.4 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
SciCodecoding · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable2−16.1 ptvs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
Artificial Analysis Intelligence Indexcomposite · indexIndependentreasoningonversion4.3conditions differ across rows → partially comparable2−27.8vs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
LiveBenchgeneral · global_averageOfficial boardreasoning_effortxhighrelease2026-06-25conditions differ across rows → partially comparable1−11.5 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
LiveBench Data Analysisgeneral · average score · variant=Data AnalysisOfficial boardvariantData Analysisreasoning_effortxhighrelease2026-06-25conditions differ across rows → partially comparable1−10.2 ptvs gpt-6-astra25 Jun 2026livebench.aiT2
LiveBench Languagegeneral · average score · variant=LanguageOfficial boardvariantLanguagereasoning_effortxhighrelease2026-06-25conditions differ across rows → partially comparable1−17.2 ptvs Claude Fable 525 Jun 2026livebench.aiT2
LiveBench Instruction Followinginstruction-following · average score · variant=IFOfficial boardvariantIFreasoning_effortxhighrelease2026-06-25conditions differ across rows → partially comparable1−11.3 ptvs Gemini 3.8 Flash25 Jun 2026livebench.aiT2
Humanity's Last Examknowledge · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable2−27.3 ptvs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
LiveBench Mathematicsmath · average score · variant=MathematicsOfficial boardvariantMathematicsreasoning_effortxhighrelease2026-06-25conditions differ across rows → partially comparable1−8.64 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
MMMU-Promultimodal · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable2−13.4 ptvs gpt-6-astraobs. 12 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantDiamondreasoningonconditions differ across rows → partially comparable1non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=GPQA Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantGPQA Diamond1−9.09 ptvs gpt-6-astraobs. 11 Sept 2026artificialanalysis.aiT2
LiveBench Reasoningreasoning · average score · variant=ReasoningOfficial boardvariantReasoningreasoning_effortxhighrelease2026-06-25conditions differ across rows → partially comparable1−14.3 ptvs gpt-6-astra25 Jun 2026livebench.aiT2

Current rows only, grouped by benchmark → canonical metric → comparability group (task configuration). Effort variants folded into this model appear as rows of the same group. 22 current rows in total. “vs leader” compares with the current leader of the benchmark's primary group only; other groups are not directly comparable. Comparability rules →

Providers & Pricing4

All offers in the price terminal →
Provider deployments, cheapest output first
ProviderContextInput / 1MCached inOutput / 1MBatch in / outStatusObservedSource
OpenRoutercheapest outputthinkingmachines/inkling:free1.05Mout 262.1K——active19 min agosince 11 Sept 2026openrouter.aiT2
OpenRouterthinkingmachines/inkling:batch524.3Kout 471.9K$0.17—active19 min agosince 11 Sept 2026openrouter.aiT2
OpenRouterthinkingmachines/inkling524.3Kout 471.9K$0.17—active19 min agosince 12 Sept 2026openrouter.aiT2
Together AIinkling—$0.17$1 / $4.05active11 h agosince 11 Sept 2026together.aiT1

USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 2 providers

Output price history of Inkling$0$1$2$3$4$5Sept 26Sept 26Sept 26Sept 26OpenRouter: first observed → $4.05 · 11 Sept 2026OpenRouter: $4.05 → $0 · 11 Sept 2026Together AI: first observed → $4.05 · 11 Sept 2026OpenRouter: $0 → $4.05 · 12 Sept 2026
  • OpenRouter
  • Together AI
  • OpenRouter$0 → $4.0512 Sept 2026
  • Together AIfirst observed $4.0511 Sept 2026
  • OpenRouter$4.05 → $011 Sept 2026
  • OpenRouterfirst observed $4.0511 Sept 2026

Input price · USD / 1M tokens 2 providers

Input price history of Inkling$0$0.20$0.40$0.60$0.80$1$1.2Sept 26Sept 26Sept 26Sept 26OpenRouter: first observed → $1 · 11 Sept 2026OpenRouter: $1 → $0 · 11 Sept 2026Together AI: first observed → $1 · 11 Sept 2026OpenRouter: $0 → $1 · 12 Sept 2026
  • OpenRouter
  • Together AI
  • OpenRouter$0 → $112 Sept 2026
  • Together AIfirst observed $111 Sept 2026
  • OpenRouter$1 → $011 Sept 2026
  • OpenRouterfirst observed $111 Sept 2026

Lineage

Open in Graph →
Explicit derived_from / fine_tuned_from / distilled_from relations stated by sources; artifacts collapsed by kind.
DESCENDANTS 0 · ARTIFACTS1 quantizationartifacts · collapsed1 quantization — artifacts · collapsedInklingthis modelInkling — this model

    Versions & Artifacts1

    Version history

    Context window2 changes

    11 Sept 2026→11 Sept 2026→12 Sept 2026current

    Max output1 change

    11 Sept 2026→12 Sept 2026current

    Opennessfirst observation only

    11 Sept 2026current

    Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.

    Artifacts 1

    quantization 1

    Timeline10

    Full timeline →
    • Price changedModelInklingThinking Machines

      OpenRouter changed pricing for Inkling: $1 in / $4.05 out per 1M tokens → $1 in / $4.05 out per 1M tokens

      $1 in / $4.05 out→$1 in / $4.05 outopenrouter
      openrouter.ai
    • Max output changedModelInklingThinking Machines

      Inkling: max output tokens changed from 32768 to 471859

      Max output32.8K tokens→471.9K tokensopenrouter
      openrouter.ai
    • Benchmark resultModelInklingThinking Machines

      Inkling scores 55.06% on Terminal-Bench

      artificial_analysis
      artificialanalysis.ai
    • Benchmark resultModelInklingThinking Machines

      Inkling scores 1.01% on Terminal-Bench

      artificial_analysis
      artificialanalysis.ai
    • Benchmark resultModelInklingThinking Machines

      Inkling scores 73.47% on MMMU-Pro

      artificial_analysis
      artificialanalysis.ai
    • Benchmark resultModelInklingThinking Machines

      Inkling scores 46.99% on SciCode

      artificial_analysis
      artificialanalysis.ai
    • Benchmark resultModelInklingThinking Machines

      Inkling scores 31.88% on Humanity's Last Exam

      artificial_analysis
      artificialanalysis.ai
    • Benchmark resultModelInklingThinking Machines

      Inkling scores 87.17% on GPQA Diamond

      artificial_analysis
      artificialanalysis.ai
    • Benchmark resultModelInklingThinking Machines

      Inkling scores 25.54 on Artificial Analysis Intelligence Index

      artificial_analysis
      artificialanalysis.ai
    • Context window changedModelInklingThinking Machines

      Inkling: context length changed from 1000000 to 1048576

      Context window1M tokens→1.05M tokensopenrouter
      openrouter.ai

    Change history

    Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.
    1 claims · 1 propertiesShow all properties

    Weights availableweights_available1

    Claim history for Weights available
    ValueValid from → toStatusSourceConfidenceExtractor
    Yes → currentcurrentAI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2highderived

    Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

    Provenance

    Attributed facts

    20

    Source tiers

    T220

    Freshest observation

    1 h ago

    Conflicts

    None

    Source documents 5

    Source documents
    SourceDocumentTypeTierLast observedSnapshots
    Together AI — pricingtogether.ai/pricing pricingT1· Official1 h ago1
    OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary19 min ago10
    Artificial Analysisartificialanalysis.ai/leaderboards/models leaderboardT2· Quality secondary3 h ago2
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/unsloth/inkling-GGUF model_pageT2· Quality secondary6 h ago4
    LiveBenchlivebench.ai/table_2026_06_25.csv leaderboardT2· Quality secondary11 h ago1

    Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

    Data quality (60/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →