# Kimi K2.7 Code HighSpeed

> The high-speed version of Moonshot AI's dedicated coding model, offering faster output for interactive coding.

## Key facts

- Model author: Moonshot AI
- Input: $1.90 per 1M tokens
- Output: $8.00 per 1M tokens
- Cached input: $0.38 per 1M tokens
- Context window: 262,144 tokens
- Input modalities: image, text, video
- Output modalities: text
- Capabilities: reasoning, tools
- Model IDs: `moonshotai/kimi-k2.7-code-highspeed`
- Model page: https://www.realrelay.ai/model/moonshot-ai/kimi-k2.7-code-highspeed

## Overview

Kimi K2.7 Code HighSpeed is the high-speed version of Moonshot AI's dedicated coding model. It runs the same underlying model with a higher output speed, giving a more responsive coding experience. It accepts text, image and video input, supports tool calling, and has a 256K-token context window.

Kimi K2.7 Code HighSpeed has a 256K-token context window. It accepts text, image and video input and returns text output.

## Capabilities

Kimi K2.7 Code HighSpeed supports reasoning and tool calling. It accepts text, image and video as input and produces text as output.

Output speed is the documented difference: the model generates tokens faster, with the highest rates in short-context requests. Thinking is always on, and the model supports tool calls, JSON mode and automatic context caching.

## Pricing

Kimi K2.7 Code HighSpeed costs $1.90 per 1M input tokens and $8.00 per 1M output tokens. Cache reads are $0.38 per 1M tokens.

Kimi K2.7 Code HighSpeed is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Kimi K2.7 Code HighSpeed where waiting on output slows you down, such as interactive coding assistants, inline code edits and agent loops with many short tool-call rounds.

Image and video input also let it turn a UI screenshot or screen recording into code quickly, with a 256K-token window for the surrounding project.

## Call it

OpenAI-compatible chat completions:

```bash
curl https://www.realrelay.ai/v1/chat/completions \
  -H "Authorization: Bearer $REALRELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "moonshotai/kimi-k2.7-code-highspeed", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Kimi K2.7 Code HighSpeed?

Kimi K2.7 Code HighSpeed is the high-speed version of Moonshot AI's dedicated coding model. It supports reasoning and tool calling and accepts text, image and video input.

### How much does Kimi K2.7 Code HighSpeed cost?

Kimi K2.7 Code HighSpeed costs $1.90 per 1M input tokens and $8.00 per 1M output tokens, with cache reads at $0.38 per 1M tokens.

### What is the context window of Kimi K2.7 Code HighSpeed?

Kimi K2.7 Code HighSpeed has a 256K-token context window.

### What inputs and outputs does Kimi K2.7 Code HighSpeed support?

Kimi K2.7 Code HighSpeed accepts text, image and video input and returns text output.

### Does Kimi K2.7 Code HighSpeed support tool calling?

Yes. Kimi K2.7 Code HighSpeed supports tool calling, so it can call functions you define and use the results in multi-step tasks. It also supports reasoning.

### How do I call Kimi K2.7 Code HighSpeed via the API?

Call Kimi K2.7 Code HighSpeed through RealRelay's OpenAI-compatible API using the model ID moonshotai/kimi-k2.7-code-highspeed.