What is the cheapest Thinking Machines model?

Inkling Small is currently Thinking Machines's cheapest paid tracked model at $0.3 per 1M input tokens and $1.2 per 1M output tokens.

How many Thinking Machines models are tracked?

2 current Thinking Machines models are tracked, each linked to the official pricing page. The dataset is refreshed twice daily.

Does Thinking Machines offer cached-input pricing?

Thinking Machines lists cached-input (prompt-caching) prices for 2 tracked models — cached input is billed at a discount when a prompt prefix repeats.

Thinking Machines

Commercial provider · 2 models tracked · Founded 2025

AI research lab founded by former OpenAI CTO Mira Murati. Its Inkling family ships as open weights on Hugging Face and is also sold as a first-party token-billed service through Tinker, the lab's fine-tuning and serverless-inference platform, from $0.30/1M input and $1.20/1M output.

Price history Website Pricing page

Thinking Machines pricing at a glanceAugust 2026 · $ per 1M tokens

Thinking Machines API pricing (August 2026): 2 current models range from $0.300 to $1.00 per 1M input tokens and $1.20 to $4.05 per 1M output tokens. The cheapest paid model is Inkling Small at $0.300/1M input; the priciest is Inkling at $1.00/1M input / $4.05 output. Every price links to Thinking Machines's official pricing page and refreshes twice daily.

Models2

Input range$0.300–$1.00

Output range$1.20–$4.05

Cached-input tiers2

Today's Thinking Machines prices

2 models · cheapest blended first

Sorted by blended cost (cheapest first). Prices per 1M tokens, August 2026 — every price links to Thinking Machines's official pricing page.

Current Thinking Machines model prices per 1M tokens, sorted by blended cost
Model	Blended*	Input	Output	Cached in	Relative cost	Context	Status
Inkling Small	$0.525	$0.300	$1.20	$0.060		262K	Current
Inkling	$1.76	$1.00	$4.05	$0.170		262K	Current

* Blended = (3×input + 1×output) ÷ 4 $/1M tokens · cheap · mid · expensive MODELPRICEWATCH.COM · 2026-08-01

Quick stats

Models tracked: 2
Type: commercial
Founded: 2025
Cheapest model: Inkling Small
Cheapest blended: $0.525/M

Open-weight models

2 open-weight models available from this provider.

Inkling

$1.00/M in · 262K ctx

Inkling Small

$0.300/M in · 262K ctx

Run it yourself

Self-host Thinking Machines's open-weight models

These models ship with open weights, so you can serve them yourself on rented GPUs instead of paying per-token API prices — often cheaper at scale.

RunPod →

Rent GPUs by the second and serve any open-weight model yourself.

Novita AI →

Serverless open-model inference billed per token — no GPU ops.

Vast.ai →

GPU marketplace — rent spot/on-demand GPUs cheaply and serve any open-weight model.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.