# Kimi K3.1 Pro Highspeed

> Kimi K3.1 Pro Highspeed is a proprietary language model from Moonshot AI, released on 23 Oct 2026. It accepts text, images and video and generates text, with a 1M-token context window and up to 1M output tokens per response. As of 2 Nov 2026, the lowest listed API price is $2 per million input tokens and $10 per million output tokens (Moonshot AI API), across 4 providers we track.

Source page: https://www.aimodel.directory/models/kimi-k3-1-pro
Last verified: 2 Nov 2026

## Specifications

- **Developer:** Moonshot AI
- **Release date:** 23 Oct 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/moonshotai/models/kimi-k3.1-pro-highspeed.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/moonshotai/models/kimi-k3.1-pro-highspeed.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/moonshotai/models/kimi-k3.1-pro-highspeed.toml)
- **Context window:** 1M (1,048,576 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/moonshotai/models/kimi-k3.1-pro-highspeed.toml)
- **Max output:** 1M tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/moonshotai/models/kimi-k3.1-pro-highspeed.toml)
- **Input:** Text, images and video (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/moonshotai/models/kimi-k3.1-pro-highspeed.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/moonshotai/models/kimi-k3.1-pro-highspeed.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/moonshotai/models/kimi-k3.1-pro-highspeed.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/moonshotai/models/kimi-k3.1-pro-highspeed.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/moonshotai/models/kimi-k3.1-pro-highspeed.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Moonshot AI API | $2 | $10 | $0.20 | 1M |
| Novita AI | $2 | $10 | $0.20 | 1M |
| Vercel AI Gateway | $2 | $10 | $0.20 | 1M |
| OpenRouter | $2 | $10 | $0.20 | 1M |
| Moonshot AI API | $4 | $20 | $0.20 | 1M |
| Novita AI | $4 | $20 | $0.20 | 1M |

## FAQ

### What is the context window of Kimi K3.1 Pro Highspeed?

Kimi K3.1 Pro Highspeed has a context window of 1,048,576 tokens (1M) and can generate up to 1,048,576 tokens in a single response, according to models.dev.

### How much does the Kimi K3.1 Pro Highspeed API cost?

Through Moonshot AI API, Kimi K3.1 Pro Highspeed costs $2 per million input tokens and $10 per million output tokens. Prices last verified 2 Nov 2026.

### Is Kimi K3.1 Pro Highspeed open source?

No. Kimi K3.1 Pro Highspeed is a proprietary model; Moonshot AI has not released its weights. It is available through APIs including Moonshot AI API, Novita AI, Vercel AI Gateway, OpenRouter.

### When was Kimi K3.1 Pro Highspeed released?

Moonshot AI released Kimi K3.1 Pro Highspeed on 23 Oct 2026, according to models.dev.

### Which providers offer Kimi K3.1 Pro Highspeed?

We track Kimi K3.1 Pro Highspeed on 4 providers: Moonshot AI API, Novita AI, Vercel AI Gateway, OpenRouter.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Kimi K3.1 Pro Highspeed", https://www.aimodel.directory/models/kimi-k3-1-pro