API reference
Modelplex is OpenAI-compatible. Base URL https://api.modelplex.ai/v1, authenticate with Authorization: Bearer mk_live_…. Create keys in the console. You're billed in credits, only for successful requests.
Chat (curl)
curl https://api.modelplex.ai/v1/chat/completions \
-H "Authorization: Bearer mk_live_…" \
-H "Content-Type: application/json" \
-d '{"model":"claude-opus-4-8","messages":[{"role":"user","content":"Hello"}]}'Chat (OpenAI SDK — drop-in)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.modelplex.ai/v1",
apiKey: process.env.MODELPLEX_API_KEY, // mk_live_…
});
const res = await client.chat.completions.create({
model: "deepseek-v3.2",
messages: [{ role: "user", content: "Hello" }],
});Images (async submit → poll)
# 1) submit (async) → returns a job id
curl https://api.modelplex.ai/v1/images/generations \
-H "Authorization: Bearer mk_live_…" -H "Content-Type: application/json" \
-d '{"model":"z-image-turbo","prompt":"a red fox","n":1}'
# → { "id": "…", "status": "queued" }
# 2) poll status (or stream /events) until succeeded → signed asset URLs
curl https://api.modelplex.ai/v1/images/generations/<id> \
-H "Authorization: Bearer mk_live_…"More
- Streaming: add
"stream": trueto chat for SSE. - Videos:
/v1/videos/generations(same async flow). - Audio:
/v1/audio/speech,/v1/audio/transcriptions. - Tools:
/v1/responses(web search / function / MCP). - Reference uploads:
/v1/uploadsfor i2i / i2v.