Skip to main content
The Model Catalog lets you browse all available ZeroGPU models and compare pricing across the tasks you care about. It’s useful when you’re selecting which model identifier to send to POST /v1/responses.

​
What you can do here

You can:
  • Search for models with Search models...
  • Filter models by Task (for example, Summarization or Text Classification)
  • Filter models by Use Case (for example, Advertisement, Email Filtering, Content Detection)
  • Clear filters to return to the full list

​
How model cards are structured

Each model is shown as a card with the following key fields:
  • Model ID: the string you will pass in the request body as model
  • Task & provider: what it’s for (task) and who published/owns it (provider)
  • Description: a short human-readable summary
  • Parameters / Context / Architecture:
    • Parameters: approximate parameter count (e.g. 60M, 90M)
    • Context: maximum context window (e.g. 400)
    • Architecture: e.g. ONNX
  • Pricing:
    • $X / 1M input
    • $Y / 1M output

​
Models shown in the catalog

​
zlm-v1-summary-cloud

  • Task: Summarization
  • Provider: ZeroGPU
  • Description: Fast lightweight model for text summarization.
  • Details: Parameters: 60M, Context: 400, Architecture: ONNX
  • Pricing: $0.20 / 1M input, $0.40 / 1M output

​
nli-deberta-v3-small

  • Task: Text Classification
  • Provider: Microsoft
  • Description: Fast lightweight model for text classification.
  • Details: Parameters: 60M, Context: 400, Architecture: ONNX
  • Pricing: $0.20 / 1M input, $0.40 / 1M output

​
zlm-v1-iab-classify-edge

  • Task: Text Classification
  • Provider: ZeroGPU
  • Description: Fast lightweight model for IAB classification.
  • Details: Parameters: 90M, Context: 400, Architecture: ONNX
  • Pricing: $0.25 / 1M input, $0.40 / 1M output

​
zlm-v1-iab-classify-edge-enriched

  • Task: Text Classification
  • Provider: ZeroGPU
  • Description: Fast lightweight model for IAB classification.
  • Details: Parameters: 90M, Context: 400, Architecture: ONNX
  • Pricing: $0.25 / 1M input, $0.40 / 1M output

​
Using a model from the catalog in an API request

Once you’ve picked a model card, copy the Model ID and set it in your request: 
{
  "model": "zlm-v1-summary-cloud"
}
The rest of the request (headers and input) follows the standard POST /v1/responses format.