Jobs
Returns all supported inference models with GPU tier requirements and ETH pricing.
Retrieve the full model catalog with per-model pricing in both wei and ETH. Models are organized by GPU tier: Tier 1 (8GB VRAM, entry-level), Tier 2 (12GB VRAM, mid-range), and Tier 3 (16GB+ VRAM, high-end). Use this to display pricing or validate model IDs before submitting jobs.
Endpoint
GET
/api/jobs/submitResponse
Example Usage
Response
{
"ok": true,
"data": {
"currency": "ETH",
"models": [
{ "id": "llama-3.1-8b-compressed", "tier": 1, "costWei": "1200000000000000", "costEth": "0.0012" },
{ "id": "mistral-7b-compressed", "tier": 1, "costWei": "800000000000000", "costEth": "0.0008" },
{ "id": "qwen-2.5-32b-compressed", "tier": 2, "costWei": "2500000000000000", "costEth": "0.0025" },
{ "id": "llama-3.1-70b-compressed", "tier": 3, "costWei": "5000000000000000", "costEth": "0.0050" }
]
}
}