Thinking Machines: Inkling — pricing & benchmarks

By thinkingmachines · Updated 2026-10-06 · Open weights · apache-2.0Reads imagesreads images / documentsaudiostep-by-step reasoningopen weights / self-hostable

What Thinking Machines: Inkling is used for

Thinking Machines: Inkling is best suited for reads images / documents, audio, step-by-step reasoning, open weights / self-hostable. Access it through one Appmo API key alongside 458 other models — Appmo's optimizer can route to it automatically when it is the best value for a request. Weights: huggingface.co/thinkingmachines/Inkling.

Use it via the Appmo API (OpenAI-compatible)

curl https://appmo.com/v1/chat/completions \
  -H "Authorization: Bearer $APPMO_KEY" \
  -d '{"model":"thinkingmachines/inkling","messages":[{"role":"user","content":"Hello"}]}'

FAQ

How much does Thinking Machines: Inkling cost?
Thinking Machines: Inkling costs $0.95 per 1M input tokens and $4.05 per 1M output tokens ($1.725 blended), as of 2026-10-06. Prices are expected to fall as competition increases.

What is Thinking Machines: Inkling best for?
Thinking Machines: Inkling is best suited for reads images / documents, audio, step-by-step reasoning, open weights / self-hostable.

How do I use Thinking Machines: Inkling?
Send requests to Appmo's OpenAI-compatible endpoint with model id "thinkingmachines/inkling" and one API key — no separate provider account needed.

Is Thinking Machines: Inkling open source?
Yes — its weights are public on Hugging Face (thinkingmachines/Inkling) under the apache-2.0 license; check the license terms before commercial use.

Can Thinking Machines: Inkling create images?
No. Thinking Machines: Inkling can read and understand images, but it only writes text.