Use any AI model with one API key

1. Get an API key

Sign in, top up your balance, and create a key from the dashboard. Keep it secret — it's shown only once.

2. Configure the endpoint

Base URL:

https://api.crosspond.uk/v1

Authenticate with a standard bearer token: Authorization: Bearer YOUR_CROSSPOND_KEY

3. Make a request (Node.js)

Install the OpenAI SDK: npm install openai

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.CROSSPOND_API_KEY,
  baseURL: "https://api.crosspond.uk/v1",
});

const completion = await client.chat.completions.create({
  model: "anthropic/claude-opus-4.8", // any supported model slug
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Explain mobile money in one sentence." },
  ],
});

console.log(completion.choices[0].message.content);

4. Streaming

Set stream: true and iterate the chunks as they arrive.

const stream = await client.chat.completions.create({
  model: "openai/gpt-4o-mini",
  messages: [{ role: "user", content: "Write a haiku about the ocean." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

Or just use curl

curl https://api.crosspond.uk/v1/chat/completions \
  -H "Authorization: Bearer $CROSSPOND_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.5-flash",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'