CN8 is an AI gateway: a single proxy layer that gives you access to AI capabilities — chatbots with RAG, multi-agent orchestration, LLM completions, dubbing, TTS, media generation, and production-grade video/audio processing — all through one consistent API with unified auth, billing, and usage tracking.
Image Captioning
studio-caption
Send an image URL (or several) plus an optional prompt and get a caption back synchronously. The caption is at data.response; per-image dimensions are in images_meta.
POST imageUrl (single) OR imageUrls (multiple) with an optional prompt. The caption comes back at data.response, along with images_meta (per-image dimensions). Synchronous — no job polling.
POST/v1/proxy/studio-analyze-caption
Caption an image (synchronous)
Parameters
Name
Type
Required
Description
imageUrl
string
optional
Public URL of one image. Send imageUrl OR imageUrls.
imageUrls
array<string>
optional
Multi-image input — returns one shared caption describing all the images together.
prompt
string
optional
Instruction for the caption. Default: "Describe the image(s) in detail."
max_new_tokens
integer
optional
Maximum caption length, in tokens. Default 512.
curl -X POST https://api.cn8.io/v1/proxy/studio-analyze-caption \
-H "X-API-Key: <cn8_api_key>" \
-H "Content-Type: application/json" \
-d '{"imageUrl":"https://example.com/file","imageUrls":["https://example.com/file"],"prompt":"your text here"}'
Response
{
"status": "success",
"data": {
"status": "success",
"response": "A sunlit park with a wooden bench under a large oak tree.",
"images_meta": [{ "width": 1600, "height": 738 }]
}
}
Field names
The caption is at data.response (NOT data.caption). Per-image dimensions are in images_meta (a plural array).
