Inkling Small
Inkling Small is a large language model made by Thinking Machines, added to the catalog on 30 Jul 2026. It has a context window of 524,288 tokens and costs $0.45 per 1M input tokens and $1.20 per 1M output tokens. It accepts text, images and audio and produces text. Typical uses: working with long text inputs, generating text from image inputs and generating text from audio inputs.
Price checked · source: OpenRouter
What Inkling Small is
Thinking Machines: Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab. It accepts text, image, and audio inputs and produces text. The catalog lists 12B active parameters out of 276B total. Its context window holds up to 524,288 tokens, and its maximum output is 262,144 tokens. The context limit describes how much material can be supplied for a request, while the output limit describes the maximum generated response. These capacities are relevant when assessing requests with substantial source material or lengthy desired text. Inkling Small produces text rather than image or audio output.
The model supports tools and reasoning. Those capabilities may suit requests that use tools or call for reasoning alongside text generation. Its listed input types also make it relevant to workflows where a text response is based on text, image, or audio input. The facts do not specify particular image or audio tasks, individual tool integrations, or the format of tool results, so those details should not be assumed. The model’s context and output limits are separate measures, and each may matter when planning a request: a large source must fit within the context window, while the generated response must fit within the output limit. The stated specifications describe a text-producing model with multimodal inputs, tool support, and reasoning support.
Key features
- Accepts text, image, and audio inputs
- Produces text
- Context window of 524,288 tokens
- Maximum output of 262,144 tokens
- Supports tools and reasoning
Typical uses
- Working with long text inputs
- Generating text from image inputs
- Generating text from audio inputs
- Tool-assisted reasoning
Inkling Small pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $0.45 | $0.36 |
| Output, per 1M tokens | $1.20 | $0.96 |
| Cached input read, per 1M tokens | $0.10 | $0.08 |
| Variant | Model id |
|---|---|
| Batch | thinkingmachines/inkling-small:batch |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 30 Jul 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0006 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.012 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.016 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.069 |
Inkling Small specifications
| Model id | thinkingmachines/inkling-small |
|---|---|
| Version | inkling-small-20260730 |
| Context window | 524,288 tokensAbout 393,216 English words |
| Max output | 262,144 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 30 Jul 2026 |
| Input types | text, image, audio |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | No |
| 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 Small yet.
Compare Inkling Small
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.