Sign in to use the playground
Run this model with your Chutes account, quota, and API access.
Model facts & API quick start
Kimi K2.6 (moonshotai/Kimi-K2.6-TEE) is served on Chutes inside a Trusted Execution Environment (TEE). Call it through the OpenAI-compatible API at https://llm.chutes.ai/v1 with a Chutes API key and "model": "moonshotai/Kimi-K2.6-TEE".
Kimi K2.6 at a glance
- Model ID
moonshotai/Kimi-K2.6-TEE- Developer
- Moonshot
- Deployed by
- chutes
- Type
- LLM
- Input price
- $0.45 per 1M tokens
- Output price
- $1.95 per 1M tokens
- Cached input price
- $0.045 per 1M tokens
- Context length
- 262,144 tokens
- Modalities
- text, image, video in → text out
- Confidential compute (TEE)
- Yes, runs in a Trusted Execution Environment
- Precision
- Native INT4 quantization (upstream), served in a TEE on Chutes
- Open weights
moonshotai/Kimi-K2.6- Parameters
- 1T total
- Active parameters
- 32B per token
- Architecture
- Native multimodal Mixture-of-Experts transformer with Multi-head Latent Attention (MLA) and a 400M-parameter MoonViT vision encoder; 61 layers, 384 experts, 8 selected per token plus 1 shared
- License
- Modified MIT
- Released
- 2026-04
- Experts
- 384 routed + 1 shared, 8 selected per token
- Layers
- 61 (1 dense)
- Attention
- MLA, 64 heads, hidden dimension 7168
- Vision encoder
- MoonViT, 400M parameters
- Vocabulary
- ~160K tokens
- Modes
- Thinking (default) and Instant, toggled via chat_template_kwargs
API quick start
- Base URL
https://llm.chutes.ai/v1- model
moonshotai/Kimi-K2.6-TEE- Endpoint
POST /v1/chat/completions- Auth header
Authorization: Bearer $CHUTES_API_KEY
OpenAI-compatible: point any OpenAI SDK at the base URL above and pass your Chutes API key as the API key.
curl -X POST "https://llm.chutes.ai/v1/chat/completions" \
-H "Authorization: Bearer $CHUTES_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moonshotai/Kimi-K2.6-TEE",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"stream": true,
"max_tokens": 1024,
"temperature": 0.7
}'Kimi K2.6 FAQ
What context window does Kimi K2.6 support?
262,144 tokens (256K), per the upstream config's max_position_embeddings. Moonshot's own benchmark runs use the full 262,144-token context.
Does Kimi K2.6 accept images and video?
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.
How do I switch between Thinking and Instant modes?
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.
Can I use Kimi K2.6 commercially?
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.
What does the TEE suffix mean?
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.
How do I call it from the OpenAI SDK?
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.
How good is it at coding, really?
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.
What is preserve_thinking mode?
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}}.