LLM models
Kimi K3
On this page
Frontier coding, native vision, and 1M-token agents from Moonshot AI.
| modelId | kimi-k3 |
| Modality | text |
| Pricing | See this model on the Pricing page for the current per-call price (with your markup). |
Operations
| Operation | modelId | Endpoint | Required input |
|---|---|---|---|
| Default | kimi-k3 | POST /api/v1/generate | prompt |
| Poll task | — | GET /api/v1/task/{id}?model=kimi-k3 | — |
Input parameters
| Field | Type | Required | Values / example |
|---|---|---|---|
| prompt | string | Yes | Text value (example: Refactor this into an iterative version and explain the trade-off: a recursive directory walk that returns every file path under a root, currently blowing the… — full value in the request example) |
| memory | boolean | No | Automatically append previous messages to maintain multi-turn context. May increase token usage. (true/false) (default: false) |
| reasoning_effort | string | No | Control reasoning depth: Low for faster responses, High for deeper analysis (options: Low | Medium | High | XHigh) (default: High) |
| thinking | boolean | No | Include the model's thinking process in the response (true/false) (default: false) |
| max_tokens | number | No | Maximum response length. Kimi K3 supports a 1M-token context; leave empty for the default. (range 1-128000) |
| system | string | No | System instruction for the model. Defaults to "You are Kimi K3, developed by Moonshot AI." when omitted. |
| messages | array | No | A conversation instead of a single `prompt`: up to 20 objects of { "role", "content" }, where role is user, assistant or system. Send `prompt` or `messages`, not both. Do not flatten a conversation into one prompt with "User:" / "Assistant:" labels — the model reads that as a single message, and a model using web search then searches for the whole block instead of your question. |
Example request
bash
curl -X POST https://you.bot/api/v1/generate \
-H "Authorization: Bearer $YOUBOT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"modelId":"kimi-k3","input":{"prompt":"Refactor this into an iterative version and explain the trade-off: a recursive directory walk that returns every file path under a root, currently blowing the stack on deep trees. Give the rewritten function, then three sentences on what you gained, what you gave up, and the input size where the difference starts to matter.","memory":false,"reasoning_effort":"High","thinking":false,"max_tokens":1}}'