Skip to main content
Kimi-K2.6 is the latest and most intelligent model by MoonShot (月之暗面), available through Anyfast via an OpenAI-compatible interface. Compared with Kimi-K2.5, it delivers major gains in agentic coding, long-context reasoning, long-horizon execution, and front-end design, and supports text, image, and video input as well as thinking and non-thinking modes.

​
Key capabilities

  • OpenAI-compatible — Works as a drop-in replacement with the OpenAI SDK
  • 256K context — 262,144 tokens for large documents and multi-turn conversations
  • Multimodal input — Accepts text, image, and video content
  • Thinking mode — Toggle via the thinking parameter; returns reasoning_content and supports Preserved Thinking
  • Long-horizon coding — More reliable across languages (Rust, Go, Python) and tasks (front-end, ops, performance)
  • Rich features — Tool Calls (function calling), JSON Mode, Partial Mode, web search, and automatic context caching

​
Quick example

curl https://www.anyfast.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.6",
    "messages": [
      { "role": "user", "content": "Explain quantum entanglement in simple terms." }
    ]
  }'
Note: image_url and video_url accept two formats: a base64 data URI (data:image/png;base64,... / data:video/mp4;base64,...) or a file reference (ms://<file_id>). Tokens served from the context cache are reported in usage.prompt_tokens_details.cached_tokens.

​
Parameters

ParameterTypeRequiredDescription
modelstringYesMust be kimi-k2.6
messagesarrayYesList of { role, content } objects. content may be a string or a multimodal array of text/image_url/video_url
thinkingobjectNoControls thinking mode, e.g. {"type": "enabled"} (default) or {"type": "disabled"}; keep: "all" enables Preserved Thinking
max_completion_tokensintegerNoMaximum tokens to generate. (max_tokens is deprecated and not honored)
temperaturefloatNo0–2. Controls randomness. Default: 1
streambooleanNoEnable SSE streaming. Default: false
top_pfloatNoNucleus sampling threshold. Default: 1
response_formatobjectNoSet to {"type": "json_object"} to enable JSON Mode
toolsarrayNoA list of tools the model may call (function calling)
stopstring / arrayNoSequences that stop generation (up to 5, max 32 bytes each)

API Reference

View the interactive API playground for Kimi-K2.6.