API flagship model for long-horizon coding and knowledge work
Reasoning effort and up-to-1M context availability
k3
Kimi Code K3 model ID
Plan entitlement and context setting
k3-256k
Kimi Code K3 model with 256k context
Video input and compacting when switching from longer context
kimi-k2.6
Conversation, code generation, vision, video, and agent tasks
Lower context than K3
kimi-for-coding
Kimi Code routine development and code completion
Use the exact model ID in third-party tools
Plain answer
Kimi model names matter because product surfaces and API model IDs are not interchangeable. In Kimi Code, k3 and k3-256k refer to Kimi K3 choices, while kimi-for-coding and kimi-for-coding-highspeed refer to Kimi K2.7 Code choices.
For the Kimi API, kimi-k3 is the flagship long-context model and kimi-k2.6 is the flexible model for text, image, video, conversation, code generation, and agent tasks.
AI handoff prompt and permissions
Copy this prompt into Kimi Code, K3Nova, or another AI agent. Keep approval manual for file writes, shell commands, account actions, and secrets.
Copyable AI prompt
Use this to give the agent the task and safety boundary in one message.
You are my AI agent for this task: choose the right Kimi model or Kimi Code model ID for my workload by context length, tool surface, speed, and entitlement.
Start by restating the goal and the permissions you need.
Use official docs or the files I provide before making claims.
Give me a direct answer first, then a short table or checklist.
If commands are needed, show exact copyable commands without a shell prompt.
Ask before writing files, running shell commands, deleting or moving data, logging in, spending money, changing account settings, or handling API keys.
Stop and ask me when a step requires secrets, payment, account access, destructive cleanup, or a permission broader than the task.
Recommended AI permissions
Permission
Give AI
Why
Public research
Allow official docs, cited public pages, and web search results.
Needed to refresh facts without touching private data.
Local files
Do not allow local file access unless you name a folder for inspection.
Most research pages do not need your machine.
Write or shell
Ask before Write, Edit, Bash, or any command execution.
Keeps the task reviewable.
Sensitive actions
Deny login, payment, API keys, account changes, and private screenshots.
Those actions need a human decision.
How to read the facts
K3
Use for long-horizon coding, end-to-end knowledge work, and deep reasoning where context length and quality matter more than raw speed.
K3-256k
Use when your job fits inside 256k context and you want a K3 path that can reduce quota pressure.
K2.6 and K2.7 Code
Use these when you need flexible multimodal chat, routine coding, or high-speed code output depending on the client.
Quick scan cards
kimi-k3
API flagship model for long-horizon coding and knowledge work Reasoning effort and up-to-1M context availability
k3
Kimi Code K3 model ID Plan entitlement and context setting
k3-256k
Kimi Code K3 model with 256k context Video input and compacting when switching from longer context
kimi-k2.6
Conversation, code generation, vision, video, and agent tasks Lower context than K3
kimi-for-coding
Kimi Code routine development and code completion Use the exact model ID in third-party tools
FAQ
Is Kimi K3 the same as k3?
k3 is the Kimi Code model ID for Kimi K3. In the API, the model ID is kimi-k3.
When should I use k3-256k?
Use it when your coding session fits inside 256k context and you want to reduce consumption compared with 1M context.
Why did my model switch fail?
Check the exact model ID, plan entitlement, context setting, and whether the tool supports the requested reasoning effort.
K3Nova