Question 1

What context window does Kimi K2.6 support?

Accepted Answer

262,144 tokens (256K), per the upstream config's max_position_embeddings. Moonshot's own benchmark runs use the full 262,144-token context.

Question 2

Does Kimi K2.6 accept images and video?

Accepted Answer

Yes. It is natively multimodal with a 400M-parameter MoonViT vision encoder, and the model card shows image and video input via OpenAI-style image_url and video_url content parts. Note the card marks video chat as experimental outside Moonshot's official API. Output is text only.

Question 3

How do I switch between Thinking and Instant modes?

Accepted Answer

Thinking mode is the default and returns reasoning content. For Instant mode on vLLM-based deployments like this chute, pass extra_body={"chat_template_kwargs": {"thinking": false}} in your request. Moonshot recommends temperature 1.0 for Thinking and 0.6 for Instant.

Question 4

Can I use Kimi K2.6 commercially?

Accepted Answer

The weights and code are released under a Modified MIT license. It is broadly permissive, but it is not identical to plain MIT, so review the LICENSE file in the Hugging Face repo before redistribution or large-scale commercial deployment.

Question 5

What does the TEE suffix mean?

Accepted Answer

The chute runs inference inside a Trusted Execution Environment, i.e. attested confidential-compute hardware. Prompts and outputs are processed inside the enclave. It is a serving-level property and does not change model outputs.

Question 6

How do I call it from the OpenAI SDK?

Accepted Answer

Point the client at base_url https://llm.chutes.ai/v1 with your Chutes API key and set model to moonshotai/Kimi-K2.6-TEE. Streaming is supported on chat and text completions.

Question 7

How good is it at coding, really?

Accepted Answer

The model card reports 80.2 on SWE-Bench Verified, 58.6 on SWE-Bench Pro (above the GPT-5.4 and Claude Opus 4.6 numbers it cites), 76.7 on SWE-Bench Multilingual, and 66.7 on Terminal-Bench 2.0. Moonshot positions it for long-horizon, end-to-end coding tasks rather than single-file snippets.

Question 8

What is preserve_thinking mode?

Accepted Answer

An option that retains the model's full reasoning content across multi-turn interactions instead of dropping it, which the card says improves coding-agent performance. On vLLM deployments enable it with extra_body={"chat_template_kwargs": {"thinking": true, "preserve_thinking": true}}.

Kimi K2.6

Sign in to use the playground

Kimi K2.6

Sign in to use the playground