Motif 3
Motif 3 is a large language model made by Motif Technologies, added to the catalog on 2 Nov 2026. It has a context window of 262,144 tokens and costs $0.30 per 1M input tokens and $1.20 per 1M output tokens. It accepts text and produces text. Typical uses: english and Korean text generation, summarising long documents and text-based question answering.
Price checked ยท source: OpenRouter
What Motif 3 is
Motif 3 is a general-purpose multilingual language model from Motif Technologies. It accepts text and produces text, and the catalog identifies English and Korean as supported languages. It is described as a Mixture-of-Experts model. The available description does not complete its note about particular strengths, so no more specific specialty is stated here. Its documented capabilities centre on working with text; images and audio are not listed as input or output modalities.
The model has a context length of 262,144 tokens and a maximum output length of 235,929 tokens. These limits can accommodate substantial text inputs and long generated responses, depending on the request. Motif 3 supports reasoning, tools, structured outputs, and response-format controls. Those features suit workflows that call tools, request a specified output structure, or involve reasoning over text. Possible tasks include drafting, summarising, answering questions, and producing structured content in English or Korean. The catalog does not specify particular tools or output schemas, so these should be treated as supported capabilities rather than assumptions about a specific integration. The context and output limits are separate listed capacities and do not mean every interaction will use the maximum. Motif 3 is described as a general-purpose model, with its stated languages, text modality, context, and interaction features defining its documented scope.
Key features
- Accepts text and produces text
- Supports English and Korean
- Has a 262,144-token context length
- Supports reasoning, tools, structured outputs, and response formats
- Allows outputs of up to 235,929 tokens
Typical uses
- English and Korean text generation
- Summarising long documents
- Text-based question answering
- Structured response generation
- Reasoning over text
Motif 3 pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.30 |
| Output, per 1M tokens | $1.20 |
| Cached input read, per 1M tokens | $0.06 |
No price change since it was added on 2 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 | $0.0085 |
| 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 |
Motif 3 specifications
| Model id | motif-technologies/motif-3 |
|---|---|
| Version | motif-3 |
| Context window | 262,144 tokensAbout 196,608 English words |
| Max output | 235,929 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 2 Nov 2026 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| 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 Motif 3 yet.