Skip to content
ModelCap

Inkling Small

Current board #83NewOpen weights

Thinking Machines·thinkingmachines/inkling-small

Inkling Small is a language model published by Thinking Machines. 2 OpenRouter endpoints are published in the latest snapshot. It accepts text, image, audio input and returns text. The published context limit is 524K tokens. The catalogue declares support for reasoning, tool use.

ModelCap Index · Current board
29.0#83
Measured · 2% support · score interval 29.0–48.6
Market Gravity
25.2
Secondary market signal
Input
$0.45
per 1M tokens
Output
$1.20
per 1M tokens
Context
524K
tokens
Providers
2
endpoints
Gateway spend
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
DeepInfrafp8Cheapest$0.45$1.20524Kfp8100.0%
Together$0.50$1.20524K

Hugging Face Inference Providers

Exact repository identity

Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.

ProviderInputOutputContextTTFTThroughputFeatures
baseten
live
$0.50$1.201.0M157 ms233.9 tok/stools · structured
deepinfra
live
$0.45$1.20524K325 ms39.4 tok/stools

Reported evaluation leads (7)

Excluded from score

Structured rows reported in this exact model repository at the pinned revision below. They are useful research leads, but remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
cais/hle
hle
31.6
Unpinned
not published
Reported
Quarantined
Idavidrein/gpqa
diamond
89.5
Unpinned
not published
Reported
Quarantined
MathArena/aime_2026
MathArena/aime_2026
95.5
Unpinned
not published
Reported
Quarantined
MathArena/hmmt_feb_2026
MathArena/hmmt_feb_2026
90.2
Unpinned
not published
Reported
Quarantined
MMMU/MMMU_Pro
mmmu_pro_standard_10_options
74
Unpinned
not published
Reported
Quarantined
ScaleAI/SWE-bench_Pro
SWE_Bench_Pro
55.9
Unpinned
not published
Reported
Quarantined
SWE-bench/SWE-bench_Verified
swe_bench_%_resolved
80.2
Unpinned
not published
Reported
Quarantined

ModelCap Index · Current board

Methodology
29.0
Measured · 1 public benchmark observation across 1 board
Current board
#83
Public rank basis
Measured (measured)
Index support
2.1% · weak
Index interval
29.0–48.6
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Identity binding
Exact catalogue product · thinkingmachines/thinkingmachines/inkling-small · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata thinkingmachines/Inkling-Small@8cc5877b44d343f88b92086aa1fb72897950f06a (not the evaluation revision)
Direct benchmark observations
1
Breadth-adjusted BES point estimate
38.8
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
63.4
Evidence status
provisional · 2% mass
General preference
Coding
Agents & tools
Reasoning
63.4
Evidence breadth
3%
Evidence coverage
2%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
14.4
Liquidity (providers × uptime)
39.7
Open reach (HF downloads)
16.9
Surface (context / tools / modalities)
95.3
Freshness
97.0
  • · OpenRouter popularity #131
  • · 2 live providers
  • · HF 30d downloads 25340
  • · Catalogue: context 524288, reasoning, tools, modalities Text/Image/Audio
  • · First seen 2026-07-30

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
82.8
strong · 94% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
100.0
Deployability
99.0
Evaluation provenance
37.9

Missing: artifactReproducibility.base-lineage, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
25.2
OpenRouter weekly popularity
#131 of 298

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Awaiting evaluation

This model is visible because it is available in the live catalogue, but it has no trustworthy community result yet. ModelCap does not infer a quality score from price, features, or market activity.

Market Gravity breakdown

Usage55%
14.4

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
39.7

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
16.9

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
97.0

Time since first public availability, on a six-month half-life.

Specification

Context window
524K tokens
Max output
262K tokens
Inputs
Text, Image, Audio
Outputs
Text
Tokenizer
Other
Cached input tokens
$0.10 / 1M
First seen on OpenRouter
30 Jul 2026

Capabilities

  • Supported: Reasoning
  • Supported: Tool use
  • Not supported: Structured output
  • Not supported: Response format
  • Not supported: Moderated

Weights & access

Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.

Access
Open weights
Licence
apache-2.0
Pinned revision
8cc5877b44d3
Parameters
266.0B
Architecture
InklingForConditionalGeneration
Model type
inkling_mm_model
Hugging Face downloads (30d)
25K
Downloads (all time)
25K
Likes
335
Repository updated
31 Jul 2026, 00:39 UTC