# Moonshot: kimi-k2.6

- Model ID: `kimi-k2.6`
- Provider: Moonshot
- Web version: https://www.moleapi.com/en/models/moonshot/kimi-k2.6
- Content status: verified

## Model introduction

Kimi K2.6 is a practical Moonshot AI model for multimodal understanding, coding, long-context analysis, and agent workflows.

## Model capabilities

- OpenAI compatible
- Responses API
- Anthropic compatible
- Gemini compatible
- Prompt cache
- Reasoning

### Verified specifications

- Official positioning: Multimodal, coding, and agent workflows
- Input / output: Text, visual input / Text
- Verified capabilities: Coding assistance, long-text analysis, tool workflows

## Model pricing and access

Pricing is supplied dynamically by the MoleAPI console API.

### Standard (default, x1)

- Input: $0.95 / 1M tokens
- Output: $4 / 1M tokens
- Cache read: $0.1 / 1M tokens
- Cache write: $1 / 1M tokens

### Discount (discount, x0.8)

- Input: $0.76 / 1M tokens
- Output: $3.2 / 1M tokens
- Cache read: $0.08 / 1M tokens
- Cache write: $0.8 / 1M tokens

### Relay (relay, x0.3)

- Input: $0.285 / 1M tokens
- Output: $1.2 / 1M tokens
- Cache read: $0.03 / 1M tokens
- Cache write: $0.3 / 1M tokens

### Temporary (availability may vary) (temp, x0.1)

- Input: $0.095 / 1M tokens
- Output: $0.4 / 1M tokens
- Cache read: $0.01 / 1M tokens
- Cache write: $0.1 / 1M tokens

### Access protocols

| Protocol | Method | Endpoint |
| --- | --- | --- |
| openai | POST | /v1/chat/completions |
| openai-response | POST | /v1/responses |
| anthropic | POST | /v1/messages |
| gemini | POST | /v1beta/models/{model}:generateContent |
| openai-response-compact | POST | /v1/responses/compact |
| openai-alpha-search | POST | /v1/alpha/search |

- Live pricing source: https://home.moleapi.com/api/pricing

## About kimi-k2.6

Kimi K2.6 is a practical Moonshot AI model for multimodal understanding, coding, long-context analysis, and agent workflows.

### Best for

Code and UI generation, screenshot and document understanding, multi-step tool tasks, and cost-sensitive agents.

### Core strengths

- Combines text, visual context, code, and structured reasoning.
- Fits planning, tool calls, and iterative execution.
- Offers a pragmatic cost-capability balance below the flagship tier.

### Limitations

- Exact context, output, and multimodal formats vary by platform configuration.
- Network access, code execution, and external actions still require compatible tools.

### Selection and production evaluation

Start a kimi-k2.6 evaluation by mapping its official positioning to real work: Code and UI generation, screenshot and document understanding, multi-step tool tasks, and cost-sensitive agents. The first pass should exercise both its main strength, "Combines text, visual context, code, and structured reasoning.", and its known limitation, "Exact context, output, and multimodal formats vary by platform configuration.", instead of relying on a single subjective general-chat comparison.

For access, MoleAPI currently lists openai, openai-response, anthropic, gemini, openai-response-compact, openai-alpha-search protocols and the Standard, Discount, Relay, Temporary (availability may vary) billing groups for this Moonshot model; the default price summary is Input $0.95 / 1M tokens · Output $4 / 1M tokens. Pricing, protocols, and groups come from the live catalog, so production planning should still price representative requests using real context length, output size, and cache-hit assumptions.

No independent ranking is shown unless it matches this exact model ID and reasoning profile, so nearby variants are not used as a proxy. Before launch, pin the model ID, prompt, and sample set, then compare task accuracy, structured-output validity, tool-call success, and timeout rates under the same conditions.

The model material on this page was last checked on 2026-07-24. When upstream model cards, context limits, or tool support change, update the cited bilingual facts before changing the recommendation; live MoleAPI price changes remain separate and update from the catalog automatically.

### Sources

- [B.AI Kimi K2.6 model guide](https://docs.b.ai/llmservice/models/kimi-k2.6/) — B.AI
- Last verified: 2026-07-24

## Code examples

### cURL

```bash
curl https://api.moleapi.com/v1/responses \
  -H "Authorization: Bearer $MOLEAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"kimi-k2.6","input":"Explain this problem step by step."}'
```

### Python

```python
from openai import OpenAI

client = OpenAI(base_url="https://api.moleapi.com/v1", api_key="YOUR_MOLEAPI_API_KEY")
response = client.responses.create(model="kimi-k2.6", input="Explain this problem step by step.")
print(response.output_text)
```

### TypeScript

```typescript
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.moleapi.com/v1", apiKey: process.env.MOLEAPI_API_KEY });
const response = await client.responses.create({ model: "kimi-k2.6", input: "Explain this problem step by step." });
console.log(response.output_text);
```

## More related models

- [kimi-k3](https://www.moleapi.com/en/models/moonshot/kimi-k3) — Moonshot
- [kimi-k2.7-code](https://www.moleapi.com/en/models/moonshot/kimi-k2.7-code) — Moonshot
- [kimi-k2.5](https://www.moleapi.com/en/models/moonshot/kimi-k2.5) — Moonshot
- [gpt-5.6-luna](https://www.moleapi.com/en/models/openai/gpt-5.6-luna) — OpenAI
- [gpt-5.6-sol](https://www.moleapi.com/en/models/openai/gpt-5.6-sol) — OpenAI
- [gpt-5.6-terra](https://www.moleapi.com/en/models/openai/gpt-5.6-terra) — OpenAI

## Frequently asked questions

### How is kimi-k2.6 priced?

Prices are read from the MoleAPI console API and update with model prices, context tiers, and account groups.

### How can I access kimi-k2.6?

The catalog currently lists openai, openai-response, anthropic, gemini, openai-response-compact, openai-alpha-search.

### How do I switch an existing project to kimi-k2.6?

Keep the MoleAPI API address and key, replace the model parameter, and check protocol-specific parameters.

### Where do the kimi-k2.6 details come from?

Capabilities and limitations are checked against B.AI and the other cited pages; pricing and protocols come from the MoleAPI console.