# Kimi K2.7 Code Highspeed

Canonical page: https://agentsky.dev/models/moonshotai/kimi-k2.7-code-highspeed
JSON record: https://gateway.agentsky.dev/v1/models/moonshotai/kimi-k2.7-code-highspeed

Kimi K2.7 Code Highspeed is a text and image and video-input model by Moonshot AI, available through the AgentSky API as moonshotai/kimi-k2.7-code-highspeed at $2.09 per million input tokens and $8.80 per million output tokens, with a 262K context window.

The higher-throughput serving variant of K2.7 Code, at twice the price.

## Facts

- **Model id:** `moonshotai/kimi-k2.7-code-highspeed`
- **Maker:** Moonshot AI
- **Input modalities:** Text, Image, Video
- **Context:** 262K
- **Released:** Jun 16, 2026
- **Aliases:** `moonshotai/kimi-k2.7-code-highspeed`, `moonshotai/k2.7-code-highspeed`, `kimi-k2.7-code-highspeed`

## Pricing

USD per million tokens on the default plan. Signed-in pages show your own plan's price; every response carries the cost of that call in `usage.cost`.

| Meter | Per 1M tokens |
|---|---|
| Input | $2.09 |
| Output | $8.80 |
| Cache read | $0.418 |
| Cache write | $2.09 |

## Use it

Anthropic wire base URL: `https://gateway.agentsky.dev`. OpenAI wire base URL: `https://gateway.agentsky.dev/v1`. Authenticate with an AgentSky API key (`ast_…`) and pass the model id.

### Anthropic SDK

```js
import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  baseURL: "https://gateway.agentsky.dev",
  apiKey: process.env.AGENTSKY_API_KEY, // ast_…
});

const message = await client.messages.create({
  model: "moonshotai/kimi-k2.7-code-highspeed",
  max_tokens: 256,
  messages: [{ role: "user", content: "Summarise this ticket." }],
});
console.log(message.usage.cost); // USD, in the response
```

### Claude Code

```bash
export ANTHROPIC_BASE_URL="https://gateway.agentsky.dev"
export ANTHROPIC_AUTH_TOKEN="$AGENTSKY_API_KEY"
export ANTHROPIC_MODEL="moonshotai/kimi-k2.7-code-highspeed"

claude
```

### OpenAI SDK

```js
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.agentsky.dev/v1",
  apiKey: process.env.AGENTSKY_API_KEY, // ast_…
});

const completion = await client.chat.completions.create({
  model: "moonshotai/kimi-k2.7-code-highspeed",
  messages: [{ role: "user", content: "Summarise this ticket." }],
});
console.log(completion.usage.cost); // USD, in the response
```

### Codex

```bash
export OPENAI_BASE_URL="https://gateway.agentsky.dev/v1"
export OPENAI_API_KEY="$AGENTSKY_API_KEY"

codex --model moonshotai/kimi-k2.7-code-highspeed
```

### OpenCode

```js
// opencode.json — then switch models any time with /models
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "agentsky": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "AgentSky",
      "options": {
        "baseURL": "https://gateway.agentsky.dev/v1",
        "apiKey": "{env:AGENTSKY_API_KEY}"
      },
      "models": { "moonshotai/kimi-k2.7-code-highspeed": {} }
    }
  }
}
```

## Questions

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

Kimi K2.7 Code Highspeed is a model from Moonshot AI. The higher-throughput serving variant of K2.7 Code, at twice the price.

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

$2.09 / $8.80 per million tokens at the prices shown, for input and output respectively. The exact price of every call comes back in the response as usage.cost, so you never have to compute it.

### What is the context length of Kimi K2.7 Code Highspeed?

262K tokens. These are the limits listed for this model in the current AgentSky catalog.

### Which clients can call Kimi K2.7 Code Highspeed?

Anything that speaks the Anthropic Messages API, which covers the Anthropic SDK and Claude Code or the OpenAI-compatible request format. Point the client's base URL at the gateway, use an AgentSky key, and pass moonshotai/kimi-k2.7-code-highspeed as the model.

### How do I name Kimi K2.7 Code Highspeed in a request?

The gateway accepts moonshotai/kimi-k2.7-code-highspeed, moonshotai/k2.7-code-highspeed, kimi-k2.7-code-highspeed. Any of them resolves to the same model, so an existing integration usually needs no change to its model string.

### Can Kimi K2.7 Code Highspeed read images?

Yes. Its listed input types are text, image, video. Include the image with your request; image input does not imply image generation.

### What output can Kimi K2.7 Code Highspeed produce?

The listed output types are text. This model returns text. Producing image, video or audio files requires a suitable tool or another model; it is not included in text generation.

### How should I plan a long prompt for Kimi K2.7 Code Highspeed?

Plan your instructions, conversation history and source material around the 262K-token context limit, leaving room for the response. A larger window lets you supply more relevant material; it does not make unrelated content useful.

### What would 10,000 input tokens and 2,000 output tokens cost with Kimi K2.7 Code Highspeed?

At the displayed input and output rates, the model-token subtotal is $0.0385. This example assumes uncached input and excludes additional pricing categories, tool calls and agent runtime. Actual usage determines the final charge.

### How is cached input priced for Kimi K2.7 Code Highspeed?

The catalog lists $0.418 per million cache-read tokens. Cache writes are listed at $2.09 per million tokens. Repeating a prompt does not by itself guarantee a cache hit; only usage reported as cached receives that rate.

### Does the Kimi K2.7 Code Highspeed token price cover an entire agent task?

No. The model price covers the model usage described above. A task can also incur tool and runtime charges, and several model calls may be needed to complete it. Compare total task usage when evaluating cost.

### How do I use Kimi K2.7 Code Highspeed on AgentSky?

This model is listed for API use. Use the model ID moonshotai/kimi-k2.7-code-highspeed with a supported gateway operation. The agent composer is not offered here because the current agent model menu has no compatible match.