Kimi K3.1 Pro

Moonshot's flagship thinking model for agents, coding and long documents: calls your tools, reads images and holds a 1M-token context.

Kimi K3.1 Pro (Moonshot AI, 2026-10-23) is Moonshot's flagship model for agentic coding, tool use and work over long documents. Send a prompt, or a chat history in messages, and get a text answer; images go in messages as image_url parts. Through the OpenAI-compatible Chat Completions endpoint it also calls your function tools and takes their results back.

It thinks before it answers: set reasoning_effort to low, medium (the default) or high, or none for quick replies. system_prompt and max_tokens work as usual. The model sets its own temperature and top_p, so leave them out, and force a tool call with tool_choice "required" rather than by name. Set service_tier to priority for Moonshot's faster Highspeed serving at the priority price. Set private_mode to true to keep the prompt and the answer out of FlyMyAI storage and logs (synchronous calls only).

Price per 1M tokens: $2 input, $0.20 cached input, $10 output; the priority tier costs $4, $0.20 and $20. Reasoning counts as output. It answers in text only: use the image, video and audio models to create media.

Price: $2.00 per 1M input tokens, $10.00 per 1M output tokens, cached input $0.20 per 1M.

Run Kimi K3.1 Pro via API

curl -X POST https://api.flymy.ai/api/v1/flymyai/kimi-k3_1-pro/predict \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Explain in two sentences why the sky is blue.","reasoning_effort":"low"}'

OpenAI-compatible API

Kimi K3.1 Pro also speaks the OpenAI Chat Completions protocol: use the official OpenAI SDK with base URL https://api.flymy.ai/api/v1/flymyai/kimi-k3_1-pro/openai/v1 and your FlyMy.AI API key.

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.flymy.ai/api/v1/flymyai/kimi-k3_1-pro/openai/v1", api_key=os.environ["FLYMYAI_API_KEY"])
response = client.chat.completions.create(
    model="flymyai/kimi-k3_1-pro",
    messages=[{"role": "user", "content": "What is a vector database?"}],
)
print(response.choices[0].message.content)

OpenAI-compatible API docs

API documentation · Create a free account · Pricing

Related models