Thinking Machines: Inkling 2 MiniOfficial docs

Thinking Machines: Inkling 2 Mini

byThinking Machines
Official docs

Inkling 2 Mini is a reasoning model from Thinking Machines released on Nov 21, 2026. It reads text and images and writes text, with a 1.05M token context window and up to 66K tokens per reply.

Show more

It costs $0.075 per million input tokens and $0.30 per million output tokens. Cached input bills at $0.015, 80% less than fresh input.

It supports tool calling, structured JSON output and prompt caching.

Modalities
In / out price
$0.075 / $0.30 per 1M
Context
1.05M
Max output
66K
Released
Nov 21, 2026
Knowledge cutoff
n/a
  • Tool calling
  • Structured output
  • Reasoning
  • Prompt caching
  • Open weights
  • Free to use

Inkling 2 Mini pricing

USD, as listed on Nov 22, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.

Input$0.075 / 1M tokens
Output$0.30 / 1M tokens
Cached input (read)$0.015 / 1M tokens

What Inkling 2 Mini costs per month

Pick a workload close to yours or type your own volumes.

Inkling 2 Mini per month
$6.08
Without caching
$8.78
Per request
$0.0002

Supported request parameters

What you can set when you call Inkling 2 Mini through an OpenAI compatible API.

  • Toolstools
  • Structured outputsstructured_outputs
  • Reasoningreasoning
  • Temperaturetemperature

Alternatives to Inkling 2 Mini

Models that take the same inputs and call tools, closest in price, cheaper ones first.

  • Reads text and images. Tool calling, reasoning.

    by z-aiDec 8, 2025$0.04/M input tokens$0.40/M output tokens

  • Reads text and images. Tool calling, structured output, reasoning. Served by 2 providers.

    by bytedanceJul 26, 2025$0.07/M input tokens$0.30/M output tokens2 providers

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 8 providers.

    by metaSep 2, 2026$0.10/M input tokens$0.20/M output tokens8 providers

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 8 providers.

    by metaAug 5, 2026$0.10/M input tokens$0.20/M output tokens8 providers

  • Reads text and images. Tool calling, structured output, reasoning. Served by 10 providers.

    by tencentNov 16, 2026$0.07/M input tokens$0.281/M output tokens10 providers

  • Reads text and images. Tool calling, structured output, reasoning. Served by 2 providers.

    by nex-agiSep 8, 2026$0.075/M input tokens$0.25/M output tokens2 providers

More from Thinking Machines

  • Reads text and images. Tool calling, structured output, reasoning. Served by 12 providers.

    by thinkingmachinesNov 5, 2026$0.30/M input tokens$1/M output tokens12 providers

  • Reads text and images. Tool calling, structured output, reasoning. Served by 10 providers.

    by thinkingmachinesJul 30, 2026$0.58/M input tokens$1.44/M output tokens10 providers

  • Reads text and images. Tool calling, structured output, reasoning. Served by 16 providers.

    by thinkingmachinesJul 15, 2026$1/M input tokens$4.05/M output tokens16 providers

All Thinking Machines models

Inkling 2 Mini questions

How much does the Inkling 2 Mini API cost?

$0.075 per million input tokens and $0.30 per million output tokens, with cached input at $0.015. The estimator on this page turns that into a monthly bill for your own workload.

What is the context window of Inkling 2 Mini?

1,048,576 tokens of input, and it can write up to 65,536 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.

Does Inkling 2 Mini support tool calling?

Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.

Is Inkling 2 Mini open source?

No. Thinking Machines serves it through an API only, so you cannot download the weights or host it yourself.

When was Inkling 2 Mini released?

Nov 21, 2026.

Catalog data from models.dev (MIT licensed), refreshed daily, last on Nov 22, 2026. The summary is written from these facts.