Kimi K3.1 Pro
Kimi K3.1 Pro is a large language model made by MoonshotAI, added to the catalog on 23 Oct 2026. It has a context window of 1,048,576 tokens and costs $0.24 per 1M input tokens and $8.402 per 1M output tokens. It accepts text, images and video and produces text. Typical uses: long-horizon coding, reasoning over long documents and working with image and video inputs.
Price checked · source: OpenRouter
What Kimi K3.1 Pro is
Kimi K3.1 Pro is Moonshot AI’s open-weight multimodal reasoning model and a post-trained successor to Kimi K3. Its catalog description identifies long-horizon coding as a design focus. It accepts text, image, and video input, and produces text. Requests can combine written prompts with visual material, while responses are returned as text. The model also supports reasoning, tool use, structured outputs, and response formats, which can be relevant when an application needs to guide how a request is handled or how its answer is arranged.
It has a context window of 1,048,576 tokens and a maximum output length of 943,718 tokens. This context capacity suits tasks that place extensive material in a single request, including long documents or substantial coding context. Image and video inputs extend its use to requests involving visual content alongside text. Its text output can serve for explanations, summaries, or structured responses based on the supplied input. Tool support can be used in workflows where an application provides tools for the model to call. Structured outputs and response formats allow output requirements to be specified. These features complement its text output and broad input types. The catalog does not provide further detail about performance or capabilities beyond those listed.
Key features
- Accepts text, image, and video input
- Produces text output
- Has a 1,048,576-token context window
- Supports reasoning and tool use
- Supports structured outputs and response formats
Typical uses
- Long-horizon coding
- Reasoning over long documents
- Working with image and video inputs
- Generating structured text responses
Kimi K3.1 Pro pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $0.24 | $0.372 |
| Output, per 1M tokens | $8.402 | $5.583 |
| Cached input read, per 1M tokens | $0.20 | $0.10 |
| Variant | Model id |
|---|---|
| Batch | moonshotai/kimi-k3.1-pro: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.
The price last changed on 22 Nov 2026. One price change has been recorded since Kimi K3.1 Pro was added.
| Date | Input /1M | Output /1M | Change |
|---|---|---|---|
| $0.24 | $8.402 | Price lowered | |
| $0.253 | $8.80 | Added at this price |
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0026 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.013 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.024 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.049 |
Kimi K3.1 Pro specifications
| Model id | moonshotai/kimi-k3.1-pro |
|---|---|
| Version | kimi-k3.1-pro-20261023 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 943,718 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 23 Oct 2026 |
| Input types | text, image, video |
|---|---|
| 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 Kimi K3.1 Pro yet.
Compare Kimi K3.1 Pro
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.