Inkling

Name: Inkling
Author: Thinking Machines Lab

Released

2026-07-15

Last refreshed

2026-07-15

Status

Researched 90d ago

Open sourceCommercial use: permittedMultimodalRAGAgentsLong contextVisionJSON / Tool use

Thinking Machines Lab releases · 2 in the last 12 monthsChangelog →

Specifications

Family: Inkling
Released: 2026-07-15
Context: 1M
Parameters: 975B total, 41B active
Architecture: Mixture of Experts
Specialization: general
Openness: Open source
License: Apache 2.0OSI-approvedCommercial use: permitted
Weights: Available
Code: Unknown
Training: Pretrained

Created by

Thinking Machines Lab

Building collaborative AI aligned with human values.

San Francisco, California, United States

Founded 2025

Website

Pricing

Output / 1M

$4.05

Input / 1M

$1.00

Cheapest of 3 routes · Baseten API · cache read $0.170

Providers(3)

Tinker Baseten API OpenRouter

View 3 provider routes

Links

Website HuggingFace

About

Inkling is Thinking Machines Lab's Apache-2.0 open-weight general-purpose multimodal model. It accepts text, image, and audio inputs and generates text with a 1M-token context window.

Providers(3)

Compare all 3

Compare API pricing across 3 tracked provider routes for input and output tokens, batch, and cached reads when available.

Provider	Input / 1M	Output / 1M	Cache	Route
Baseten API	$1.00	$4.05	read $0.170	ServerlessProvisioned
OpenRouter	$1.00	$4.05	read $0.170	Serverless
Tinker	$1.87	$4.68	read $0.374

Capabilities

VisionMultimodalReasoningJSON / Tool useAudioFine-tuning

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(3)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.

Benchmark	Score	Version	Evaluation	Source
FrontierMath Tier 4	4.9	FrontierMath Tier 4 v2 (private)Observed 2026-08-06	Configuration: Inkling (Extra High) Harness: Epoch AI FrontierMath Tier 4 v2 private set Evaluator: Epoch AI Confidence: confirmed Notes: Epoch AI-run evaluation (evaluator of record), from Epoch AI Benchmarking Hub data download https://epoch.ai/data/benchmark_data.zip (file frontiermath_tier_4_v2.csv, row 'Inkling_xhigh', run started 2026-08-06). Epoch data is CC BY 4.0: credit 'Epoch AI, Capabilities & benchmarking, https://epoch.ai/benchmarks'. Highest-scoring Epoch configuration for this model selected; other configurations exist in the same file. Discovered via Benchmark Heaven (lead only).	Source
Google-Proof Q&A	88.3	diamondObserved 2026-08-05	Configuration: Inkling (Extra High) Harness: Epoch AI Inspect harness (GPQA Diamond, 198 Q) Evaluator: Epoch AI Confidence: confirmed Notes: Epoch AI-run evaluation (evaluator of record), from Epoch AI Benchmarking Hub data download https://epoch.ai/data/benchmark_data.zip (file gpqa_diamond.csv, row 'Inkling_xhigh', run started 2026-08-05). Epoch data is CC BY 4.0: credit 'Epoch AI, Capabilities & benchmarking, https://epoch.ai/benchmarks'. Highest-scoring Epoch configuration for this model selected; other configurations exist in the same file. Discovered via Benchmark Heaven (lead only).	Source
ARC-AGI-2	36.5	ARC-AGI-2 semi-privateObserved 2026-10-01	Configuration: Inkling (single reported configuration) Harness: ARC Prize semi-private evaluation Evaluator: ARC Prize Foundation Confidence: confirmed Notes: ARC Prize official leaderboard data, verified in https://arcprize.org/media/data/leaderboard/v2.json (generatedAt 2026-10-01T18:51Z) modelDisplayName 'Inkling' score 0.36528 (no effort label published). Discovered via Benchmark Heaven / Epoch AI mirror (lead only).	Source