Home › Providers › thinkingmachines › Thinking Machines: Inkling

Thinking Machines: Inkling API Pricing

Thinking Machines: Inkling is an API model from thinkingmachines. It costs $1 per 1M input tokens and $4.05 per 1M output tokens, with cached input at $0.17. Its context window is 524,288 tokens with up to 471,859 output tokens. A workload of 10M input + 2M output tokens costs about $18.1 per month.
Input
$1
per 1M tokens
Output
$4.05
per 1M tokens
Cached input
$0.17
per 1M tokens
Context window
524K
524,288 tokens
Blended (80/20)
$1.61
per 1M tokens

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

How much does Thinking Machines: Inkling cost for a real workload?

At 10M input + 2M output tokens per month, Thinking Machines: Inkling costs about $18.1 ($10 input + $8.1 output). Try your own volumes in the cost calculator.

What are cheaper alternatives to Thinking Machines: Inkling?

Compare Thinking Machines: Inkling with other models

Thinking Machines: Inkling vs Thinking Machines: Inkling Small (free)Thinking Machines: Inkling vs Thinking Machines: Inkling (free)Thinking Machines: Inkling vs Thinking Machines: Inkling Small

Frequently asked questions

How much does Thinking Machines: Inkling cost?

Thinking Machines: Inkling costs $1 per 1M input tokens and $4.05 per 1M output tokens (list price, snapshot October 21, 2026). At 10M input + 2M output tokens per month that is about $18.1.

What is the context window of Thinking Machines: Inkling?

Thinking Machines: Inkling has a context window of 524,288 tokens and can return up to 471,859 output tokens per response.

What are cheaper alternatives to Thinking Machines: Inkling?

Cheaper models include OpenAI: o3 (batch) ($1 in / $4 out), OpenAI: GPT-4.1 (batch) ($1 in / $4 out), Google: Gemini 3.8 Flash ($0.825 in / $4.125 out). See the full list on this page.

Is Thinking Machines: Inkling free to use?

No. Thinking Machines: Inkling is a paid model at $1 input / $4.05 output per 1M tokens. 20 free models are listed on the free models page.

Provider: thinkingmachines · Model ID: thinkingmachines/inkling · Modality: text+image+audio->text · Price snapshot October 21, 2026, refreshed daily. How we collect prices