LLM / Text Generation API: One Key for Chat and Generative Media
TL;DR: GenRelay isn't only image and video — it also exposes a chat/LLM endpoint (currently Zhipu AI's GLM 5.2 at $1.00/1M tokens) through the same OpenAI-compatible API and the same prepaid balance as your image and video calls. Useful when your app needs both text reasoning and media generation without juggling two vendors.
Supported text model
| Model | Provider | Price |
|---|---|---|
| GLM 5.2 | Zhipu AI | $1.00 / 1M tokens |
Rates as of 2026-09-24 — see the live pricing page for current numbers and any newly added text models.
Quick start
POST https://genrelay.ai/v1/chat/completions
Authorization: Bearer YOUR_KEY
Content-Type: application/json
{
"model": "glm-5.2",
"messages": [{"role": "user", "content": "Write a 20-word product description for a ceramic mug."}]
}
Same request shape as OpenAI's chat completions endpoint — existing OpenAI SDK code works by swapping the base URL and key.
Why this matters for media-generation apps
- Prompt engineering and generation in one pipeline: use the LLM to expand a short product brief into a detailed image/video prompt, then call the image or video endpoint — all on the same API key and the same prepaid balance.
- No separate contract or billing relationship just to add a text model to an otherwise media-focused app.