Inkling 2 Mini is a large language model made by Thinking Machines, added to the catalog on 21 Nov 2026. It has a context window of 1,048,576 tokens and costs $0.075 per 1M input tokens and $0.30 per 1M output tokens. It accepts text and images and produces text. Typical uses: answering questions about supplied images, summarising long documents and producing structured text responses.
Price checked ยท source: OpenRouter
What Inkling 2 Mini is
Thinking Machines: Inkling 2 Mini is an open-weight multimodal model from Thinking Machines Lab. It accepts text and image inputs and produces text. Its context window holds up to 1,048,576 tokens, and its maximum output is 65,536 tokens. The catalog describes it as a looped transformer and lists 3.4 billion active parameters out of 26.4 billion total in a mixture-of-experts configuration. These details identify its architecture and its stated input and output limits.
Supported features include reasoning, tool use, structured outputs, and response-format controls. The model can be considered for requests that combine reasoning with a requested output structure, or that involve tools. Since it accepts images as well as text and returns text, it also fits workflows where a prompt includes visual material and asks for a written response. The listed modalities are text and images for input, and text for output.
Its context capacity makes it relevant to work involving lengthy supplied text or multiple materials in a single request, subject to the request fitting within the context limit. The output limit allows for longer text responses, though the actual response depends on the request. Suitable tasks include summarising lengthy material, describing image content in text, creating structured answers, and working through requests that use tools. The catalog does not specify particular tools or output schemas, so those depend on how the model is made available.
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 controls
Typical uses
- Answering questions about supplied images
- Summarising long documents
- Producing structured text responses
- Reasoning over supplied materials
Inkling 2 Mini pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.075 |
| Output, per 1M tokens | $0.30 |
| Cached input read, per 1M tokens | $0.015 |
The price last changed on 21 Nov 2026. 2 price changes have been recorded since Inkling 2 Mini was added.
| Date | Input /1M | Output /1M | Change |
|---|---|---|---|
| $0.075 | $0.30 | Price lowered | |
| $0.10 | $0.40 | Price raised | |
| $0.091 | $0.362 | Added at this price |
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0021 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0029 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.012 |
Inkling 2 Mini specifications
| Model id | thinkingmachines/inkling-2-mini |
|---|---|
| Version | inkling-2-mini-20261120 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 65,536 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 21 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 Mini yet.
Compare Inkling 2 Mini
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.