Integrate NeuralHub into your workflows, CI/CD pipelines, and AI agents.
All API requests must be authenticated using an API Key. You can generate an API Key in your Settings.
/v1/meVerifies your API key and returns your user ID.
{
"id": "user_123",
"email": "user@example.com"
}All endpoints are prefixed with https://api.neuralhub.xyz
https://api.neuralhub.xyzOpenAI-compatible chat completions API.
/v1/chat/completionsGenerate a response from a model based on the input messages.
{
"model": "google/gemini-2.0-flash-001",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"temperature": 0.7,
"stream": true
}{
"id": "chatcmpl-123",
"object": "chat.completion",
"created": 1677652288,
"model": "google/gemini-2.0-flash-001",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello there!"
},
"finish_reason": "stop"
}
]
}List available models for inference.
/v1/modelsList all available models.
{
"data": [
{
"id": "google/gemini-2.0-flash-001",
"object": "model",
"created": 1677652288,
"owned_by": "google"
}
]
}Manage GPU pods for fine-tuning and inference.
/v1/podsList all active GPU pods.
{
"pods": []
}/v1/podsLaunch a new GPU pod.
{
"gpu_type": "NVIDIA A100",
"image": "runpod/pytorch:2.0.1-py3.10-cuda11.8.0-devel",
"template_id": "pytorch-2.0.1"
}{
"id": "pod-123",
"status": "starting"
}