# Kimi K2.5 — Atlas Cloud API

> Powerful model for long-context and intelligent workflows.

This is the machine-readable API reference for **Kimi K2.5** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `moonshotai/kimi-k2.5`
- **Built by**: Moonshot
- **Modality**: Text
- **Context length**: 262,144 tokens
- **Max output tokens**: 262,144
- **Model page**: https://www.atlascloud.ai/models/moonshotai/kimi-k2.5
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- **Input**: $0.49 per 1M tokens
- **Output**: $2.5 per 1M tokens
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="your-api-key"
```

Then ask in plain English; the agent calls `atlas_chat` with `model: "moonshotai/kimi-k2.5"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas chat "Your prompt here" --model moonshotai/kimi-k2.5
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

This model is served over an **OpenAI-compatible** endpoint. Any OpenAI SDK works —
just override the base URL and use the Atlas Cloud model ID.

```http
POST https://api.atlascloud.ai/v1/chat/completions
Authorization: Bearer $ATLASCLOUD_API_KEY
Content-Type: application/json
```

### curl

```bash
curl -X POST "https://api.atlascloud.ai/v1/chat/completions" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "moonshotai/kimi-k2.5",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "data:image/png;base64,<BASE64_IMAGE_DATA>"
          }
        },
        {
          "type": "video_url",
          "video_url": {
            "url": "https://example.com/your-video.mp4"
          }
        },
        {
          "type": "text",
          "text": "Please describe the content of this image/video"
        }
      ]
    }
  ],
  "max_tokens": 81920,
  "temperature": 0.7,
  "stream": false
}'
```

### Python (OpenAI SDK)

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["ATLASCLOUD_API_KEY"],
    base_url="https://api.atlascloud.ai/v1",
)

response = client.chat.completions.create(
    model="moonshotai/kimi-k2.5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)
```

### Multimodal input

This model accepts image, video input alongside text. Media parts go inside `messages[].content[]`.

- **Image** — part `type: "image_url"`, with `image_url.url` set to a public URL or a `data:image/...;base64,` URI.
  - Formats: image/png, image/jpeg, image/webp, image/gif
- **Video** — part `type: "video_url"`, with `video_url.url` set to a public URL. Prefer URLs over base64 for large files.
  - Formats: video/mp4, video/mpeg, video/quicktime, video/x-msvideo, video/x-flv, video/mpg, video/webm, video/x-ms-wmv, video/3gpp

**Example request body**:

```json
{
  "model": "moonshotai/kimi-k2.5",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "data:image/png;base64,<BASE64_IMAGE_DATA>"
          }
        },
        {
          "type": "video_url",
          "video_url": {
            "url": "https://example.com/your-video.mp4"
          }
        },
        {
          "type": "text",
          "text": "Please describe the content of this image/video"
        }
      ]
    }
  ],
  "max_tokens": 81920,
  "temperature": 0.7,
  "stream": false
}
```

### Supported sampling parameters

`temperature`, `top_p`, `top_k`, `min_p`, `frequency_penalty`, `presence_penalty`, `repetition_penalty`, `seed`, `max_tokens`, `logit_bias`

Context window: 262,144 tokens.

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

### Kimi K2.5 Large Language Model

#### Overview

**Kimi K2.5** is an advanced large language model developed by **Moonshot AI**, designed to deliver **high-quality reasoning, ultra-long context comprehension, and professional-grade language generation**. It is an enhanced iteration within the Kimi model family, focusing on improved reliability, stronger analytical performance, and better alignment with real-world, high-complexity use cases.

Kimi K2.5 is particularly optimized for **document-centric intelligence**, making it suitable for enterprise knowledge systems, research assistants, and applications where long-context understanding and accuracy are critical.

---

#### Model Positioning

Kimi K2.5 is positioned as a **reasoning- and context-oriented foundation model**, rather than a purely conversational model. Its primary goal is to support tasks that require:

* Sustained attention across long inputs
* Precise interpretation of complex instructions
* Structured reasoning over large bodies of text
* Stable and predictable output behavior

This positioning makes Kimi K2.5 especially well suited for **professional, enterprise, and research-oriented AI products**.

---

#### Design Philosophy

The design of Kimi K2.5 emphasizes **depth over superficial fluency**. Instead of optimizing solely for short responses or casual chat, the model focuses on:

* Preserving semantic coherence across long documents
* Maintaining logical consistency throughout multi-step reasoning
* Reducing hallucinations in factual and analytical outputs
* Respecting instruction hierarchy and task constraints

This approach allows Kimi K2.5 to perform reliably in scenarios where correctness, traceability, and clarity are more important than creativity or stylistic variation.

---

#### Key Capabilities

##### Ultra-Long Context Processing

Kimi K2.5 is designed to process **very large context inputs**, enabling it to:

_(Description truncated. Full text on the model page.)_

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/moonshotai/kimi-k2.5 · Docs: https://www.atlascloud.ai/docs