Thinkingmachines

Inkling Small

Launched 2026-07-30 · Listed on OpenRouter 2026-07-30

Prices updated . Benchmarks updated .

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

You send / 1M

$0.450

tokens in

It replies / 1M

$1.20

tokens out

Context

524K

tokens it can read at once

Typical request

$0.0012

1,000 words in, 400 out

Benchmarks

BenchmarkScoreKindDateSource
Epoch Capabilities Index150.5Independent2026-07-15Epoch AI
GPQA DiamondExtra high effort88.5%Independent2026-08-14Epoch AI
OTIS Mock AIMEExtra high effort90.0%Independent2026-08-14Epoch AI
SimpleQA VerifiedExtra high effort19.1%Independent2026-08-27Epoch AI
ARC-AGI-2Extra high effort40.1%Independent2026-07-15ARC Prize, republished by Epoch AI
CritPt8.3%Independent2026-07-15CritPt, republished by Epoch AI
Arena Elo (text)1,414Independent2026-10-28LMArena
Arena Elo (webdev)1,409Independent2026-10-28LMArena
Arena Elo (vision)1,237Independent2026-10-19LMArena

Rankings on this site use the Epoch Capabilities Index, an independent composite. Lab-reported rows are the lab's own figures and are kept separate.

Data privacy

No training or retention: Yes. At least one provider serves it with zero data retention.

ProviderYou send / 1MIt replies / 1MUptimePrivacy policy
DeepInfra · fp4$0.450$1.20100%Read

Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.

What it can do

  • Reads: text, image, audio
  • Writes: text
  • Weights: Open weights
  • Reasoning: Yes
  • Tool calling: Yes
  • Longest reply: 524K tokens
  • Repeated text is billed at $0.100 per 1M (prompt caching)

Compare with

Appears in

Estimate your monthly cost with Inkling Small

Sources and licenses

  • OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
  • Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
  • models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
  • Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
  • LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
  • Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
  • What a score measures: the benchmark guide.