# Kimi K2.6 API

Moonshot's Kimi K2.6, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

- Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
- The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send kimi-k2.6 as the model.
- Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

## Facts

- Model name: kimi-k2.6
- Maker: Moonshot
- Context window: 262.1K tokens
- Input price: $0.894 per million tokens
- Output price: $3.713 per million tokens
- Providers: 1 independent provider
- Regions: global

## Providers

- [EmpirioLabs AI](https://liquidinference.ai/providers/4f49f07c-0d26-44bd-88a8-34f3f5fbd3b7.md): global, $0.894 input and $3.713 output per million tokens, $0.179 cache read per million tokens, 262.1K tokens of context

## Scores

- HLE: 37.5, #62 of 273
- GPQA: 91.1, #35 of 250
- AA-LCR: 81.0, #34 of 237
- SciCode: 51.5, #46 of 123
- Terminal-Bench Hard: 43.9, #20 of 166
- τ²-Bench: 95.9, #11 of 169
- IFBench: 76.0, #13 of 178
- SimpleQA Verified: 34.9, #60 of 126

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

## Request

```sh
curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.6",
    "messages": [{"role":"user","content":"Say hello."}]
  }'
```

## Questions

### What is Kimi K2.6?

Served by intent-router: each job goes to the cheapest healthy upstream for this model.

### How much does Kimi K2.6 cost?

Offers now ask $0.894 per million input tokens and $3.713 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.

### What is the context length of Kimi K2.6?

The largest offer takes 262,144 input tokens. One job can generate up to 16,000 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.

### What can Kimi K2.6 do?

Its providers list Vision, Video input, Reasoning budget, Reasoning effort, JSON object, JSON schema, Stop sequences, Top-p sampling, Text, Tools.

### What inputs and outputs does Kimi K2.6 support?

Text · Images · Video → Text.

### Which providers serve Kimi K2.6?

1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.

### How do I call Kimi K2.6?

Send "kimi-k2.6" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.

### When was Kimi K2.6 listed?

The exchange first listed it on 10/8/2026. This is not its release date.

## Related pages

- [This page in a browser](https://liquidinference.ai/models/kimi-k2.6)
- [Kimi K3](https://liquidinference.ai/models/kimi-k3.md)
- [Kimi k2.6:thinking](https://liquidinference.ai/models/kimi-k2.6%3Athinking.md)
- [Kimi K2 Instruct 0905](https://liquidinference.ai/models/kimi-k2-instruct-0905.md)
- [Kimi K2 Instruct FP4](https://liquidinference.ai/models/kimi-k2-instruct-fp4.md)
- [Kimi K2 Instruct](https://liquidinference.ai/models/kimi-k2-instruct.md)
- [Kimi K2 Instruct Fast](https://liquidinference.ai/models/kimi-k2-instruct-fast.md)
- [Set up a client](https://liquidinference.ai/connect/kimi-k2.6)
- [All models](https://liquidinference.ai/models)
- [Providers](https://liquidinference.ai/providers.md)
- [Discover the best model for your budget](https://liquidinference.ai/discover)
- [Quickstart](https://liquidinference.ai/docs/quickstart.md)
- [llms.txt: the index of every page, as Markdown](https://liquidinference.ai/llms.txt)
- [llms-full.txt: every page in one file](https://liquidinference.ai/llms-full.txt)