Transend AI API Platform

Ship multi-model AI experiences with a single base URL, one API key, and familiar OpenAI-compatible schemas.

Get API Key · Quickstart · Playground

---

Overview

• Unified interface — Switch models by changing the model field; the request schema mirrors OpenAI’s Chat Completions.
• Multimodal coverage — Text, chat, image, video, audio, and speech APIs under the same gateway.
• Task management — Long-running jobs expose task_id, status polling, and result URLs.
• Resilience — Edge routing, automatic failover, and global POPs keep latency low.
• Security & audit — Fine-grained API keys, rate controls, and workspace audit logs.

When to use it

• Product teams: prototype new AI-powered features without juggling multiple vendors.
• Developers: ship production workloads using one SDK across all providers.
• Data/ops teams: track cost, latency, and fallback behaviour centrally.

---

Quickstart

1. Create an API key — Visit the Transend AI console and generate a workspace key. Store it securely, e.g. export TRANSEND_API_KEY=sk-....
2. Choose a model — This guide uses gpt-5-mini; see the model catalog for alternatives.
3. Send your first request — Copy one of the samples below (curl, Node, Python). All return an assistant response immediately.

HTTP (curl)

curl -X POST "https://api.transendai.net/v1/texts/chat/completions" \
  -H "Authorization: Bearer $TRANSEND_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5-mini",
    "messages": [
      {"role": "system", "content": "You are a concise assistant."},
      {"role": "user", "content": "Give me a one-line product pitch."}
    ],
    "max_tokens": 160
  }'

Node.js (fetch)

const res = await fetch("https://api.transendai.net/v1/texts/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.TRANSEND_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "gpt-5-mini",
    messages: [{ role: "user", content: "Draft a release note headline." }],
  }),
});

const data = await res.json();
console.log(data.choices?.[0]?.message?.content);

Python (requests)

import os
import requests

API_KEY = os.environ["TRANSEND_API_KEY"]
url = "https://api.transendai.net/v1/texts/chat/completions"

payload = {
    "model": "gpt-5-mini",
    "messages": [
        {"role": "system", "content": "You are a marketing assistant."},
        {"role": "user", "content": "Summarize our launch in two sentences."}
    ],
}

resp = requests.post(
    url,
    headers={"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"},
    json=payload,
    timeout=30,
)
resp.raise_for_status()
print(resp.json()["choices"][0]["message"]["content"])

---

API Reference Snapshot

Endpoint

• POST https://api.transendai.net/v1/texts/chat/completions

Sample response

{
  "id": "chatcmpl-123",
  "model": "gpt-5-mini",
  "usage": { "prompt_tokens": 32, "completion_tokens": 68, "total_tokens": 100 },
  "choices": [
    {
      "index": 0,
      "finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "Transend AI is the control plane for every frontier model in one API."
      }
    }
  ]
}

---

Model Catalog

Use /models or the console catalog to retrieve the latest inventory, pricing, and capability tags.

---

Asynchronous Tasks (Image & Video)

For operations that take longer than a few seconds, create a task and poll its status.

Create a task

curl -X POST "https://api.transendai.net/v1/tasks" \
  -H "Authorization: Bearer $TRANSEND_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-image",
    "type": "image_generation",
    "prompt": "A neon-lit future skyline at midnight",
    "size": "1024x1024"
  }'

Response:

{
  "task_id": "task_9c7a82",
  "status": "queued",
  "created_at": "2025-03-01T08:32:11Z"
}

Poll task status

curl "https://api.transendai.net/v1/tasks/task_9c7a82" \
  -H "Authorization: Bearer $TRANSEND_API_KEY"

Status values: queued, running, succeeded, failed. When the task completes, result_url provides a signed download link.

---

Authentication & Security

• Send every request with Authorization: Bearer <API_KEY>.
• Store API keys on the server; expose client-side calls through your own proxy or short-lived tokens.
• Configure rate limits and anomaly alerts inside the console.
• Audit logs track key creation, rotation, and workspace actions.

---

Error Handling

Each response includes x-transend-trace-id; share it with the support team for faster triage.

---

Audio quick example

curl -X POST "https://api.transendai.net/v1/audios/tts" \
  -H "Authorization: Bearer $TRANSEND_API_KEY" \
  -H "Content-Type": "application/json" \
  -d '{
    "model": "sonic-tts-fast",
    "voice": "luna",
    "input": "Welcome to Transend AI"
  }' --output welcome.mp3

---

Contact

• Console support: console.transendai.net/support
• Email: [email protected]
• Discord: discord.gg/transend-ai
• Twitter/X: @transend_ai
• Legal: Terms · Privacy

---

Launch Checklist

• Sample scripts tested (curl / Node / Python).
• Links verified (internal & external).
• Metadata (title / description / og:image) populated.
• Error codes and rate-limit guidance documented.
• Support and legal contacts surfaced.