Inkling 2 Small is a large language model made by Thinking Machines, added to the catalog on 9 Nov 2026. It has a context window of 1,048,576 tokens and costs $0.30 per 1M input tokens and $1.00 per 1M output tokens. It accepts text and images and produces text. Typical uses: reasoning over text and image inputs, summarising long documents and answering questions about supplied material.
Price checked ยท source: OpenRouter
What Inkling 2 Small is
Inkling 2 Small is an open-weight multimodal reasoning model from Thinking Machines Lab. It accepts text and image inputs and produces text. Its stated context window is 1,048,576 tokens, and its maximum output is 943,718 tokens. This gives applications room to provide extensive context or request long text outputs, within the stated limits. The model is described as a mixture-of-experts system with 17 billion active parameters out of 594 billion total.
It supports reasoning, tool use, structured outputs, and response-format settings. These options allow an application to make tools available or request responses in a structured format. Text and image inputs can be supplied together for tasks that use both written context and visual material. The model's text output suits drafting, summarising, answering questions about supplied content, and generating structured responses. Since its listed output modality is text, it is a text-producing model rather than one that generates images or audio. A context window of this size can be useful when a request draws on multiple lengthy documents or substantial background material. Tool support can connect a reasoning task to available tools, while structured output support can help keep generated text in a requested format. Inkling 2 Small is suited to text and image workflows that need extended context, reasoning, or configured text output.
Key features
- Accepts text and image inputs and produces text
- Has a context window of 1,048,576 tokens
- Supports reasoning and tool use
- Supports structured outputs and response-format settings
- Maximum output is 943,718 tokens
Typical uses
- Reasoning over text and image inputs
- Summarising long documents
- Answering questions about supplied material
- Drafting text from extensive context
- Generating structured responses
Inkling 2 Small pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.30 |
| Output, per 1M tokens | $1.00 |
| Cached input read, per 1M tokens | $0.03 |
No price change since it was added on 9 Nov 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0005 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0083 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.011 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.047 |
Inkling 2 Small specifications
| Model id | thinkingmachines/inkling-2-small |
|---|---|
| Version | inkling-2-small-20261107 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 943,718 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 9 Nov 2026 |
| Input types | text, image |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Inkling 2 Small yet.
Compare Inkling 2 Small
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.