Skip to content

Thinking Machines · Chat

Inkling 2 Small

Thinking Machines 🇺🇸ChatInkling familyOpen weights. One of its sources says the weights are publicly available.
From Cloudflare Workers AI's listing:
Inkling 2 Small is a multimodal Mixture-of-Experts model from Thinking Machines Lab with 594B total and 18B active parameters and up to 1M tokens of context. It accepts text and image inputs and generates text, with built-in reasoning and tool calling.
llminfo IQ
136.8
Market median price
$0.475 blended / 1M
Max context
1M
Listings
36

Evidence and sources

🤗 thinkingmachines/Inkling-2-Small Model architecture, as its sources state it llminfo IQ 136.8, ranked among chat models. From 97 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 116.9, 95% interval 109–125. From 9 benchmark families across 4 sources. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedGood value (63.2). Cheaper per task than its benchmark results predict. From 23 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksReleased 5 Nov 2026Maker HQ: US (source)
All rankings: #31 on OpenRouter this week #48 on OpenRouter this month #53 on OpenRouter today #121 on NanoGPT recentlySources: LMArena data, Cloudflare Workers AI, Models.dev data, AI/ML API data, llminfo researchPrimary data from LMArena from Cloudflare Workers AI: architecture, description from Models.dev: weights availability from AI/ML API: primary mode from llminfo research: release date
Tags from its sources:instructtoolsreasoningvision

Advantages and trade-offs

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

Advantages

Open weights available

The weights are public. 3 of the 9 peers that say either way have open weights.

Trade-offs

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 8 maker's prices; 2 market median prices.

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt caching

Listings

 Flowdotthinkingmachines/inkling-2-small:free · freeSource: FlowDot data1M$0.00$0.00——
 Hugging FaceInference by Primeintellectthinkingmachines/Inkling-2-SmallSource: Hugging Face Inference Providers data1M$0.15$0.50——
 Kilothinkingmachines/inkling-2-smallSources: Kilo AI Gateway data, Models.dev data1M$0.15cache read $0.03$0.50——
 OpenRouterInference by Primeintellectthinkingmachines/inkling-2-small · fp4Source: OpenRouter data docs1M$0.15cache read $0.03$0.50248415ms
 Primethinkingmachines/inkling-2-smallSource: Models.dev data1M$0.15cache read $0.03$0.50cache write $0.15——
 Eden AIInference by Cloudflare Workers AIcloudflare/@cf/thinkingmachines/inkling-2-smallSource: Models.dev data1M$0.30cache read $0.10$1.00——
 NanoGPTTEE/inkling-2-small · teeSources: Models.dev data, NanoGPT524K$0.30cache read $0.03$1.00——
 Nous Portalthinkingmachines/inkling-2-smallSource: Nous Portal Inference Gateway data1M$0.30cache read $0.03$1.00——
 Vercelthinkingmachines/inkling-2-smallSources: Models.dev data, Vercel AI Gateway data1M$0.30cache read $0.03$1.00——
 Cloudflare Workers AI@cf/thinkingmachines/inkling-2-smallSources: Cloudflare Workers AI, LiteLLM data, Models.dev data1M$0.30cache read $0.10$1.00——
Show all 33 listings

Showing 10 of 33: the cheapest per 1M input tokens from each provider.

Also sold by Cortecs AI, DeepInfra, Nebius AI Studio, Ollama, Tinfoil, Together AI.

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

Agentic

Arena AgentSource: LMArena data · Nov 2026
GDPval-AASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Source: OpenRouter benchmark exports · Nov 2026
7 Nov 2026 version · 90-day results
Across 6 providers lowest 62.7% median 63.7% highest 68.3%
Show results from 6 providersHide results from 6 providers
  • DeepInfra
  • Nebius
  • Together
  • Modal
  • PrimeIntellect
  • Cloudflare
ValsSource: Vals AI

Coding

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

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond7 results
Source: OpenRouter benchmark exports · Nov 2026
7 Nov 2026 version · 90-day results
Across 6 providers lowest 90.2% median 91.1% highest 91.4%OpenRouter's automatic routing 90.7%
Show results from 6 providers and OpenRouter's automatic routingHide results from 6 providers and OpenRouter's automatic routing
  • Nebius
  • Together
  • Cloudflare
  • Modal
  • OpenRouter's automatic routing
  • PrimeIntellect
  • DeepInfra

Reasoning

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

General

Math

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

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · Data by LLM Stats · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark

Also known as: @cf/thinkingmachines/inkling-2-small, cloudflare/@cf/thinkingmachines/inkling-2-small, deepinfra/thinkingmachines/inkling-2-small, inkling-2-small-free, nebius/thinkingmachines/inkling-2-small, tee/inkling-2-small, thinkingmachines/inkling-2-small, thinkingmachines/inkling-2-small:free, together_ai/thinkingmachines/inkling-2-small

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