Kimi K3.1 Pro 多模态推理模型，支持 1M 上下文、文本与视觉理解、函数调用。缓存写入分 5 分钟与 1 小时计价，思考 Token 包含在输出用量中。
Model ID: kimi-k3.1-pro · Type: chat · Provider: Moonshot
Endpoints: /v1/chat/completions · /v1/messages · /v1/responses
| Input (per 1M tokens) | $1.1 USD |
| Output (per 1M tokens) | $5.5 USD |
| Cache read (per 1M tokens) | $0.11 USD |
| Cache write 5m (per 1M tokens) | $1.1 USD |
| Cache write 1h (per 1M tokens) | $2.2 USD |
from openai import OpenAI
client = OpenAI(api_key="sk-...", base_url="https://api.router.ai/v1")
resp = client.chat.completions.create(
model="kimi-k3.1-pro",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)Kimi K3.1 Pro (`kimi-k3.1-pro`) is billed per usage at $1.1/1M in · $5.5/1M out, in USD. Current pricing is always listed at https://j8api.com/models/kimi-k3.1-pro.
Send a request to https://api.router.ai/v1/v1/chat/completions with the header `Authorization: Bearer <your API key>` and `"model": "kimi-k3.1-pro"`. The API is OpenAI-compatible, so any OpenAI SDK works by changing base_url to https://api.router.ai/v1 — no other code change.
Kimi K3.1 Pro can be called on: /v1/chat/completions; /v1/messages; /v1/responses.
Kimi K3.1 Pro accepts up to 1,048,576 input tokens and can return up to 1,048,576 output tokens. Requests exceeding the input limit are rejected before reaching the model.
Kimi K3.1 Pro supports: vision, function_calling, prompt_caching, thinking, input_video, structured_output.
Kimi K3.1 Pro is a chat model from Moonshot, available through the J8API gateway with the same API key as every other model.
Call it through the J8API OpenAI-compatible endpoint (API base: https://api.router.ai/v1). AI agents can browse the catalog and call any text model through MCP (https://mcp.router.ai/mcp); for image, video and other modalities use the API above.