Use JJAPI in 30 seconds

1. Buy a plan and grab your API key

After purchase you'll receive an email with a key like sk-jjapi-... and a link to your console.

2. Point your client at JJAPI

Replace the base URL in your existing OpenAI client. Everything else stays the same.

curl https://api.jjapi.net/v1/chat/completions \
  -H "Authorization: Bearer sk-jjapi-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-7",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.jjapi.net/v1",
    api_key="sk-jjapi-...",
)

r = client.chat.completions.create(
    model="claude-opus-4-7",
    messages=[{"role": "user", "content": "Hello"}],
)
print(r.choices[0].message.content)

import OpenAI from "openai";

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

const r = await client.chat.completions.create({
  model: "claude-opus-4-7",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(r.choices[0].message.content);

3. Call any model

Use the model name from any supported vendor. Switch by changing one string.

Common model identifiers

Snapshot as of 2026-05-23. New models ship roughly monthly — see the live model catalog for the always-current list.

Streaming

Add stream: true just like with OpenAI. JJAPI streams server-sent events in OpenAI format regardless of the upstream vendor.

stream = client.chat.completions.create(
    model="gpt-5.5-pro",
    messages=[{"role": "user", "content": "Stream this"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

Other endpoints

• /v1/embeddings — text embeddings (OpenAI / Cohere / Voyage)
• /v1/images/generations — DALL·E 3 / Midjourney / Flux
• /v1/audio/speech — TTS (OpenAI / ElevenLabs)
• /v1/audio/transcriptions — Whisper
• /v1/rerank — Cohere / Voyage rerankers