Inkling vs Inkling Small

At a Glance

Compare
InklingThinking Machines Lab
Inkling SmallThinking Machines Lab
Intelligence, Cost, and Efficiency
IntelligenceHigher is better · MM Intelligence v4.4#27 of 5747.4 score · 3/3 sources · complete#31 of 5735.2 score · 2/3 sources · provisional · missing LiveBench · full-core range 23.5–56.8
CostLower is better · Published-token output estimate#13 of 27$0.090 per LiveBench caseUnrankedNot in the 27-model eligible cohort
EfficiencyHigher is better · MM Efficiency v1.9#22 of 2742.0 score · 3/3 sources · completeUnrankedNot in the 27-model eligible cohort
Pricing and Limits
Input priceFrom · USD / 1M tokens$0.95Deepinfra ↗ · Oct 15, 2026$0.45Deepinfra ↗ · Oct 19, 2026
Output priceFrom · USD / 1M tokens$4.05Deepinfra ↗ · Oct 15, 2026$1.20Deepinfra ↗ · Oct 19, 2026
Context windowMaximum documented tokens1,049K1,049K
Model facts checkedSep 3, 2026View model evidence →Sep 25, 2026View model evidence →

Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →

Available Benchmarks

All benchmark results →
BenchmarkInklingInkling-Small
ARC-AGI-1verified-v1-613c385b0c93 · verified_score · leader79.5095% of row best · percent · Inkling84.00100% of row best · percent · Inkling Small (XHigh)
ARC-AGI-2verified-v2-be40992860f9 · verified_score · leader36.5391% of row best · percent · Inkling40.14100% of row best · percent · Inkling Small (XHigh)
LMArena Text Arenatext-2026-10-15-a64ca3b12b6e · arena_rating · leader1,441.38100% of row best · rating · inkling; 95% CI [1437.08506747, 1445.68368363]; votes 40648; rank 741,412.6298% of row best · rating · Inkling Small; 95% CI [1407.97725962, 1417.26957820]; votes 32304; rank 135
Overall ResultCounted from the protocol-matched rows above1 benchmark win2 benchmark winsOverall lead

Third-party benchmark Only like-for-like primary-publisher results are shown; raw scores, relative scores, configuration, and token spend remain visible.

Side-by-Side Facts

FieldInklingInkling-Small
DeveloperThinking Machines LabThinking Machines Lab
FamilyInklingInkling
ModelInklingInkling-Small
VersionInklingInkling-Small
Lifecycleactiveactive
Released2026-07-152026-07-30
Knowledge cutoffUnknownUnknown
Input modalitiesText, Image, Video, AudioText, Image, Audio
Output modalitiesTextText
Context window1,049K1,049K
Total parameters975B276B
Active parameters41B12B
Licenseapache-2.0apache-2.0
Open weightsYesYes
API availableYesYes
Self-hostableYesYes
Provider accessDeepinfra (Standard), Fireworks Ai (Standard), Openrouter (Standard), Together Ai (Standard)Deepinfra (Standard), Openrouter (Standard)
Capabilitiesagents, chat, coding, generation, reasoning, tools, visionagents, chat, coding, generation, reasoning, tools, vision

Inkling Capabilities

agentschatcodinggenerationreasoningtoolsvision
Serving providers4
Canonical IDthinkingmachines/Inkling

Inkling Small Capabilities

agentschatcodinggenerationreasoningtoolsvision
Serving providers2
Canonical IDthinkingmachines/Inkling-Small

Primary Evidence

Sources and Freshness

Questions

Inkling vs Inkling Small FAQs

Is Inkling or Inkling Small better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both Inkling and Inkling Small, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, Inkling or Inkling Small?+

Inkling is $0.95 and Inkling Small is $0.45 per million tokens, so Inkling Small is cheaper on this metric. Inkling is $4.05 and Inkling Small is $1.20 per million tokens, so Inkling Small is cheaper on this metric.

Which has a larger context window, Inkling or Inkling Small?+

Both models have the same sourced context window: 1,048,576 tokens each.

Which performs better in benchmarks, Inkling or Inkling Small?+

Inkling Small leads the current overall benchmark count. The result uses 3 protocol-matched benchmarks from 2 publishers; it is not a universal quality score.

Can Inkling or Inkling Small be self-hosted?+

Both models have the same sourced self-hosting status: supported. Inkling is open weight; Inkling Small is open weight.

Can Inkling and Inkling Small understand images?+

Inkling is documented with image input; Inkling Small is documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, Inkling or Inkling Small?+

Neither model has a sourced maximum output in this comparison, so a larger limit cannot be determined.

Do Inkling and Inkling Small support reasoning and tool use?+

Inkling: reasoning, tool calling, and image input. Inkling Small: reasoning, tool calling, and image input. Feature support does not establish relative quality.

Which is available from more inference providers, Inkling or Inkling Small?+

Inkling has 4 sourced provider routes; Inkling Small has 2, so Inkling has broader tracked availability.

Which offers better value, Inkling or Inkling Small?+

There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.

Send Feedback