Skip to main content
POST
/
responses
zlm-v1-followup-questions-edge: Responses
curl --request POST \
  --url https://api.zerogpu.ai/v1/responses \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --header 'x-project-id: <api-key>' \
  --data '
{
  "input": "Electric vehicles are gaining popularity worldwide as battery costs drop and charging infrastructure expands. Most modern EVs offer a range of 250 to 350 miles on a single charge, and fast-charging stations can replenish 80% of battery capacity in under 30 minutes. However, concerns around battery disposal, rare earth mineral sourcing, and grid capacity continue to shape the debate around large-scale EV adoption.",
  "model": "zlm-v1-followup-questions-edge"
}
'
{}

Documentation Index

Fetch the complete documentation index at: https://docs.zerogpu.ai/llms.txt

Use this file to discover all available pages before exploring further.

ZeroGPU’s zlm-v1-followup-edge is a 60M-parameter model fine-tuned specifically to generate contextual follow-up responses that drive deeper user engagement. Built for edge deployment on the ONNX runtime, it’s optimized for the kind of low-latency, conversational interactions that keep users active, think smart nudges, re-engagement prompts, and contextual suggestions. Unlike general-purpose generators, this model is laser-focused on conversational depth, making every response feel intentional rather than generic. Purpose-built for the ZeroGPU distributed inference network.
References: Model docs • Terms • Privacy

​
Specifications

PropertyValue
Model IDzlm-v1-followup-questions-edge
TaskText Generation
Typet5
Parameters120M
Version1
Max Tokens400
ProviderZeroGPU
Input Price$0.25 / 1M
Output Price$0.40 / 1M
Total Price$0.65 / 1M

​
Try it

Send a live request with your x-api-key and x-project-id. Model is fixed to zlm-v1-followup-questions-edge. Use request examples below to switch use cases (JSON extraction, NER, PII, and so on).

Authorizations

​
x-api-key
string
header
required
​
x-project-id
string
header
required

Body

application/json
​
input
string<textarea>
required

Multi-line text or document content to send to the model.

Required string length: 1 - 131072
​
instructions
string
​
metadata
object

Response

Success

The response is of type object.