Inkling

• Type: Generation
• Capabilities: vision, reasoning

Overview

Inkling is the first model released by Thinking Machines - a large Mixtrue of Experts model with 975B parameters, 41B active, trained on over 45T tokens of text, image, and audio data. It supports up to a 1M context length and and offers strong performance across the board for agentic and reasoning heavy tasks.

Reasoning efforts

• Supported: none, minimal, low, medium, high, xhigh, max

See the reasoning effort guide for request examples.

Pricing

Priority	Input Tokens (per 1M)	Output Tokens (per 1M)
Async	$0.90	$3.00
Batch (24h)	$0.60	$2.00

Playground

Open this model in the Playground.