Quick start

Connect Any AI Model via API or MCP in 2 Minutes

From zero to your first generation in four steps.

  1. 1

    Create an API key

    Sign in, open Settings → API and create a key. Copy it right away — it is shown only once.

  2. 2

    Top up your wallet

    API usage is paid from your Ropewalk wallet in coins (1 USD = 1000 coins). Any balance works, including subscription coins.

  3. 3

    Pick a model

    List the models available to you with their API prices. Use the "id" field as the model name.

    curl http://ropewalk.ai/api/v1/models -H "Authorization: Bearer rw_live_YOUR_KEY"
  4. 4

    Send your first request

    Text models speak the OpenAI Chat Completions format:

    curl http://ropewalk.ai/api/v1/chat/completions \
  -H "Authorization: Bearer rw_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "thinkingmachines/inkling", "messages": [{"role": "user", "content": "Write a tagline for a coffee shop"}]}'

Using the OpenAI SDK

Set the base URL to Ropewalk and use your Ropewalk key:

Python
from openai import OpenAI

client = OpenAI(base_url="http://ropewalk.ai/api/v1", api_key="rw_live_YOUR_KEY")

reply = client.chat.completions.create(
    model="thinkingmachines/inkling",
    messages=[{"role": "user", "content": "Write a tagline for a coffee shop"}],
)
print(reply.choices[0].message.content)
print(reply.usage)  # includes cost_coins
Node.js
import OpenAI from 'openai'

const client = new OpenAI({ baseURL: 'http://ropewalk.ai/api/v1', apiKey: 'rw_live_YOUR_KEY' })

const reply = await client.chat.completions.create({
  model: 'thinkingmachines/inkling',
  messages: [{ role: 'user', content: 'Write a tagline for a coffee shop' }],
})
console.log(reply.choices[0].message.content)

Generate an image or video

Media models run as jobs: start one, then poll until it is "succeeded". The output link is valid for one hour; poll again for a fresh one.

cURL
curl http://ropewalk.ai/api/v1/generations \
  -H "Authorization: Bearer rw_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "black-forest-labs/flux-3-image", "prompt": "A red fox in the snow, cinematic light"}'

# → {"id": "6720…", "status": "queued", ...}

curl http://ropewalk.ai/api/v1/generations/6720… -H "Authorization: Bearer rw_live_YOUR_KEY"
# → {"status": "succeeded", "output": {"url": "https://…"}, "cost_coins": 100}

Attach your own files

Image-to-video, editing and voice models take files. Upload one, then pass its id in the model's input. Not sure which keys a model takes? Use the request builder.

cURL
# 1. Upload a file from your computer
curl http://ropewalk.ai/api/v1/files -H "Authorization: Bearer rw_live_YOUR_KEY" -F "file=@photo.jpg"
# → {"id": "6721…", "object": "file", "type": "image", "url": "https://…"}

# 2. Put its id into the model's input (input keys: GET /v1/models/{id} → inputs)
curl http://ropewalk.ai/api/v1/generations \
  -H "Authorization: Bearer rw_live_YOUR_KEY" -H "Content-Type: application/json" \
  -d '{"model": "black-forest-labs/flux-3-image", "prompt": "Turn it into an anime poster", "inputs": {"image": "6721…"}}'
Open the request builder

Connect an MCP client

Claude Code: add the server, then type /mcp → Ropewalk → Authenticate, sign in and press Allow. Guides for Claude, ChatGPT and Cursor:

Claude Code
claude mcp add --transport http ropewalk http://ropewalk.ai/api/v1/mcp
MCP guides for every app
Read the full docs