Documentation

1. Quickstart

Get up and running with the iSpeed AI Platform in less than 5 minutes.

Step 1: Create an API Key

Head over to the Console and generate a new API key under the "API Keys" section.

Code Examples

curl https://api.ispeedhost.net/v1/chat/completions \
  -H "Authorization: Bearer $ISPEED_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3-70b",
    "messages": [{"role": "user", "content": "How do I use this API?"}]
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.ispeedhost.net/v1",
    api_key="your_ispeed_key"
)

response = client.chat.completions.create(
    model="llama-3-70b",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.ispeedhost.net/v1",
  apiKey: "your_ispeed_key"
});

async function main() {
  const completion = await client.chat.completions.create({
    messages: [{ role: "user", content: "Hello!" }],
    model: "llama-3-70b",
  });
  console.log(completion.choices[0]);
}
main();

File Storage (MinIO Flow)

To process large files (images, audio), upload them to our transient storage first.

1. Request a Signed URL via our /v1/storage/upload endpoint.
2. PUT your file to the provided URL.
3. Use the returned file_id in your inference request.

2. API Reference

Our gateway is fully OpenAPI 3.0 compliant. You can download the spec or explore it interactively.

OpenAPI Renderer Placeholder

SwaggerUI or Redoc will be integrated here.