MCP / Models / Language models

Kimi K3.1 Pro MCP: agentic coding and tools with no API key

Moonshot Kimi K3.1 Pro is a flagship thinking model for agents, coding and long documents: it calls your tools, reads images, holds a 1M-token context. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

Use Kimi K3.1 ProInputs and price
No API key$2.00 / $10.00 per 1M tokensChat modelMoonshot AICommercial use
Kimi K3.1 Pro sample from the FlyMy.AI catalog

$ YOUR NEXT RUN

Claude CodeCodexCursorAny agent

Use Kimi K3.1 Pro in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/kimi-k3-1-pro.md. Help me connect the FlyMy.AI MCP to this assistant, then run Kimi K3.1 Pro (flymyai/kimi-k3_1-pro) for this task: Ask Kimi K3.1 Pro: write unit tests for this Python module.
Open FlyMy.AIDownload brief

What Kimi K3.1 Pro does

Send a prompt or messages (images as image_url parts). It thinks before it answers: reasoning_effort is none, low, medium (the default) or high. Through the OpenAI-compatible endpoint it calls your function tools; force a call with tool_choice 'required'. service_tier priority buys Moonshot's faster serving and private_mode keeps the exchange out of FlyMy.AI storage.

Kimi K3.1 Pro inputs

Every input of flymyai/kimi-k3_1-pro as its live schema lists them. Returns output (string), finish_reason (string), service_tier (string), reasoning (string), stream_details (string).

InputType, values and default
# prompt
string required What to ask Kimi
# messages
string optional Chat history as a JSON array of {role, content}; used instead of the prompt
# system_prompt
string optional Instructions for the whole chat
# reasoning_effort
string optional Allowed: none, low, medium, high Default: medium How hard it thinks before answering; none answers at once
# service_tier
string optional Allowed: default, priority Default: default priority: Moonshot's faster Highspeed serving, at the priority price
# max_tokens
integer optional Allowed: 1 to 943718 Most tokens to generate, reasoning included
# private_mode
boolean optional Default: false Keep the prompt and the answer out of FlyMyAI storage and logs (synchronous requests only)

Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

“Ask Kimi K3.1 Pro: write unit tests for this Python module.”runs flymyai/kimi-k3_1-pro
“Compare these two product specs in a table with Kimi K3.1 Pro.”runs flymyai/kimi-k3_1-pro
“With Kimi K3.1 Pro, rewrite this landing page paragraph to be shorter and clearer.”runs flymyai/kimi-k3_1-pro

Kimi K3.1 Pro price

$2.00 per 1M input tokens, $10.00 per 1M output tokens, cached input $0.20 per 1M. Cached input is $0.20 per 1M tokens. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

See usage pricing →

Call Kimi K3.1 Pro from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

From an agent, through the MCP

The agent calls get_model_schema, then run_model with:

{
  "endpoint_id": "flymyai/kimi-k3_1-pro",
  "input": {
    "prompt": "Explain in two sentences what an MCP server is."
  }
}

From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. Text models answer on the streaming route.

curl -X POST https://api.flymy.ai/api/v1/flymyai/kimi-k3_1-pro/predict/stream/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Explain in two sentences what an MCP server is.'

With the OpenAI SDK

Kimi K3.1 Pro also answers the OpenAI Chat Completions protocol.

from openai import OpenAI

client = OpenAI(base_url="https://api.flymy.ai/api/v1/flymyai/kimi-k3_1-pro/openai/v1", api_key="YOUR_FLYMYAI_KEY")
reply = client.chat.completions.create(
    model="flymyai/kimi-k3_1-pro",
    messages=[{"role": "user", "content": "Explain in two sentences what an MCP server is."}],
)
print(reply.choices[0].message.content)

Questions about Kimi K3.1 Pro

Do I need a Moonshot AI API key for Kimi K3.1 Pro?

No. Kimi K3.1 Pro runs on FlyMy.AI's account, so you need no Moonshot AI key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

How much does Kimi K3.1 Pro cost?

$2.00 per 1M input tokens, $10.00 per 1M output tokens, cached input $0.20 per 1M. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-09.

How do I use Kimi K3.1 Pro in Claude Code, Codex or Cursor?

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Ask Kimi K3.1 Pro: write unit tests for this Python module." Your agent reads the inputs with get_model_schema and runs flymyai/kimi-k3_1-pro with run_model.

What does Kimi K3.1 Pro need as input?

Kimi K3.1 Pro requires prompt; it also takes 6 optional inputs, each listed on this page with its allowed values and default.

Can I call Kimi K3.1 Pro from my own code?

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/kimi-k3_1-pro/predict/stream/ with your FlyMy.AI API key in the X-API-KEY header; it also answers the OpenAI Chat Completions protocol at https://api.flymy.ai/api/v1/flymyai/kimi-k3_1-pro/openai/v1.

Go to the source

Kimi K3.1 Pro in the playground →Kimi K3.1 Pro guide in the docs →Model endpoints in the docs →Language models guide →Every model on FlyMy.AI →Every MCP in the catalog →Usage pricing →

From the FlyMy.AI model catalog of 2026-11-09: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.