Inkling-Small (Reasoning)

by Thinking Machines Lab

Inkling-Small (Reasoning) is a reasoning model from Thinking Machines Lab, released on July 30, 2026. It has a 524K-token context window and can generate up to 256K output tokens. API pricing is $0.3 per 1M input tokens and $1.2 per 1M output tokens. It ranks #51 of 220 models by Intelligence Score with a score of 38.1.

Inkling-Small is Thinking Machines Lab's efficient open-weights MoE multimodal model (276B total / 12B active parameters) released under Apache 2.0. It accepts text, image, and audio inputs and generates text, with native reasoning, variable thinking effort, and a context window up to 1M tokens (Tinker exposes 64K and 256K configurations). Hugging Face weights: thinkingmachines/Inkling-Small and thinkingmachines/Inkling-Small-NVFP4. Vendor self-host VRAM: BF16 ≥ ~600 GB aggregated; NVFP4 ≥ ~180 GB aggregated. SWE-Bench Verified 80.2% vs Inkling 77.6% (same bash-only harness). Fine-tuning and playground chat are available via Tinker. Official Tinker serverless inference (256K, list): $0.30 / $1.20 per 1M input/output tokens ($0.06 cached).

Key specs

ProviderThinking Machines Lab
Release date2026-07-30
Licenseopen source
Context window524K tokens
Max output256K tokens
Input price$0.3 / 1M tokens
Output price$1.2 / 1M tokens
Intelligence Score38.1
Coding index28.5

Quick answers

What is the context window of Inkling-Small (Reasoning)?

Inkling-Small (Reasoning) has a context window of 524K tokens, with a maximum output of 256K tokens per response.

How much does Inkling-Small (Reasoning) cost?

Inkling-Small (Reasoning) costs $0.3 per 1M input tokens and $1.2 per 1M output tokens through the API.

Is Inkling-Small (Reasoning) open source?

Yes. Inkling-Small (Reasoning) is an open model released under the open source license.

When was Inkling-Small (Reasoning) released?

Thinking Machines Lab released Inkling-Small (Reasoning) on July 30, 2026.

How does Inkling-Small (Reasoning) compare to Claude Opus 5.5 (Reasoning)?

Inkling-Small (Reasoning) scores 38.1 on the Intelligence Score versus 60.5 for Claude Opus 5.5 (Reasoning), the current #1. Input pricing is $0.3 vs $4 per 1M tokens.

Compare on the AI leaderboard · All AI models

More models from Thinking Machines Lab