One key. Every way in.●

deeprelay cli

The whole platform, one verb at a time●

One binary, no config file. Install it, log in once, and a streamed chat completion is a command in the shell you already have open.

sdks

Typed clients in Python and TypeScript●

Both are generated from the same OpenAPI spec the API serves, so the client can't drift from the endpoint it calls.

# pip install deeprelay-sdk
import os

import deeprelay_sdk

cfg = deeprelay_sdk.Configuration(
    host="https://api.deeprelay.ai/v1",
    access_token=os.environ["DEEPRELAY_API_KEY"],
)

with deeprelay_sdk.ApiClient(cfg) as client:
    models = deeprelay_sdk.InferenceApi(client).list_models(modality="chat")
    for m in models.data:
        print(f"{m.id:<36} {m.author or '-'}")

// npm install @deeprelay/sdk
const { Configuration, InferenceApi } = require('@deeprelay/sdk');

async function main() {
  const cfg = new Configuration({
    basePath: 'https://api.deeprelay.ai/v1',
    accessToken: process.env.DEEPRELAY_API_KEY,
  });
  const models = await new InferenceApi(cfg).listModels({ modality: 'chat' });
  for (const m of models.data) {
    console.log(`${m.id.padEnd(36)} ${m.author ?? '-'}`);
  }
}
main();

rest api

No SDK required●

Plain HTTPS and JSON, with cursor pagination and idempotency keys on every mutation. The model catalog is your first call: one key-scoped GET.

curl https://api.deeprelay.ai/v1/models \
  -H "Authorization: Bearer $DEEPRELAY_API_KEY"

inference

Change the base URL. Keep the code.●

Chat, images, and video speak the OpenAI wire format, so the client library you already import keeps working; swap two lines and you're billed per token instead of per hour.

import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.deeprelay.ai/v1",
    api_key=os.environ["DEEPRELAY_API_KEY"],  # never a literal key
)

stream = client.chat.completions.create(
    model="deeprelay/deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "Explain recursion in one sentence"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

mcp

Hand your coding agent the keys●

Drop this into .mcp.json and your agent can read the catalog, check spend, manage webhooks, and run inference across chat, embeddings, image and video: 29 tools in three tiers.

{
  "mcpServers": {
    "deeprelay": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@deeprelay/mcp@latest"],
      "env": {
        "DEEPRELAY_API_KEY": "${DEEPRELAY_API_KEY}"
      }
    }
  }
}

webhooks

Find out the moment a job lands●

Subscribe an HTTPS endpoint to the event types you care about. Every delivery is HMAC-signed and carries a stable event id you can dedupe on.

curl -X POST https://api.deeprelay.ai/v1/webhook-endpoints \
  -H "Authorization: Bearer $DEEPRELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com/hooks/deeprelay",
       "event_types":["video.completed","video.failed"]}'

{
  "id": "dc062a1e…",
  "type": "video.completed",
  "created_at": "2026-08-07T02:39:11Z",
  "data": {
    "video": {
      "id": "41ca1150…",
      "object": "video",
      "model": "deeprelay/wan2.7-t2v",
      "status": "completed"
    }
  }
}

v1 emits the video generation events, video.completed and video.failed, with the job nested under data.video as shown above. The webhooks guide lists every event type with its payload.