SAM 3 Segment

from $0.0100 per job

Image
0.50s
inference.segment.v2
Integrate Prodia's `inference.segment.v2` using https://docs.prodia.com/llms.txt

API request

Image inputs are sent as multipart form-data alongside the JSON job. See docs.prodia.com.

curl -X POST https://inference.prodia.com/v2/job \
  -H "Authorization: Bearer $PRODIA_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Accept: image/jpeg" \
  -d '{
  "type": "inference.segment.v2",
  "config": {
    "confidence_threshold": 0.5
  }
}'

Input

Image to be segmented using text prompts.
Limits : Max 10 MB, 4096x4096. Min 256x256.

Text prompt describing what to segment (e.g., 'yellow school bus', 'person', 'cat').

Confidence threshold for detections. Lower values return more masks, higher values only return high-confidence masks.

Output

Elapsed0.00s

Other endpoints

  • Flux Fast Schnell · Text to Imageinference.flux-fast.schnell.txt2img.v2from $0.0020 per image
  • Flux Kontext Pro · Text to Image$0.0400 per image
  • Partner Flux Kontext Pro · Text to Imageinference.partner.flux-kontext.pro.txt2img.v2$0.0400 per image
  • Flux Kontext Pro · Image Editing$0.0400 per image
  • Partner Flux Kontext Pro · Image Editinginference.partner.flux-kontext.pro.img2img.v2$0.0400 per image
  • Flux Kontext Max · Text to Image$0.0800 per image
  • Partner Flux Kontext Max · Text to Imageinference.partner.flux-kontext.max.txt2img.v2$0.0800 per image
  • Flux Kontext Max · Image Editing$0.0800 per image
  • Partner Flux Kontext Max · Image Editinginference.partner.flux-kontext.max.img2img.v2$0.0800 per image
  • Veo 3.1 · Text to Video
  • Partner Veo 3.1 · Text to Videoinference.partner.veo.txt2vid.v2
  • Veo 3.1 · Image to Video
  • Partner Veo 3.1 · Image to Videoinference.partner.veo.img2vid.v2
  • Veo Fast 3.1 · Text to Video
  • Partner Veo Fast 3.1 · Text to Videoinference.partner.veo.fast.txt2vid.v2
  • Veo Fast 3.1 · Image to Video
  • Partner Veo Fast 3.1 · Image to Videoinference.partner.veo.fast.img2vid.v2
  • Nano Banana · Image Editing$0.0390 per image
  • Partner Nano Banana · Image Editinginference.partner.nano-banana.img2img.v2$0.0390 per image
  • Nano Banana · Text to Image$0.0390 per image
  • Partner Nano Banana · Text to Imageinference.partner.nano-banana.txt2img.v2$0.0390 per image
  • Veo 3.1 Lite · Text to Videoinference.veo.lite.txt2vid.v2
  • Partner Veo 3.1 Lite · Text to Videoinference.partner.veo.lite.txt2vid.v2
  • Veo 3.1 Lite · Image to Videoinference.veo.lite.img2vid.v2
  • Partner Veo 3.1 Lite · Image to Videoinference.partner.veo.lite.img2vid.v2
  • Partner Seedance 2 · Text to Videoinference.partner.seedance-2.txt2vid.v2
  • Partner Seedance 2 · Image to Videoinference.partner.seedance-2.img2vid.v2
  • Partner Seedance 2 Fast · Text to Videoinference.partner.seedance-2.fast.txt2vid.v2
  • Partner Seedance 2 Fast · Image to Videoinference.partner.seedance-2.fast.img2vid.v2
  • Seedream 4.0 · Text to Image
  • Seedream 4.0 · Image Editing
  • Seedream 4.5 · Text to Image
  • Seedream 4.5 · Image Editing
  • Seedream 5.0 Lite · Text to Image
  • Seedream 5.0 Lite · Image Editing
  • Partner Seedance 2 5 · Text to Videoinference.partner.seedance-2-5.txt2vid.v2
  • Partner Seedance 2 5 · Image to Videoinference.partner.seedance-2-5.img2vid.v2
  • Partner Seedance 2 5 · Reference to Videoinference.partner.seedance-2-5.ref2vid.v2
  • Partner Seedance 2 · Reference to Videoinference.partner.seedance-2.ref2vid.v2
  • Partner Seedance 2 Fast · Reference to Videoinference.partner.seedance-2.fast.ref2vid.v2
  • Qwen Image Edit Plus (Speed) · Image Editing$0.0200 per image
  • Vit inference.vit.img2label.v2

Related models