One LLM generation on a rented GPU, priced per request
One LLM generation on a rented GPU, priced per request.
3192 (raw units)
price
9
calls / 30d
1
unique payers
2026-09-11
updated
Provider
api.prismnetwork.tech · discovered, not yet claimed by its owner
Payment (x402 accepts[])
[
{
"scheme": "exact",
"network": "eip155:8453",
"payTo": "0xe67a61f8e2aC4057aa22e64306107E7120078447",
"asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
"amount": "3192",
"maxTimeoutSeconds": 60
},
{
"scheme": "exact",
"network": "eip155:4663",
"payTo": "0xEcaaE714912C38fA7e0dAF78afa7C54DbeD11039",
"asset": "0x5fc5360D0400a0Fd4f2af552ADD042D716F1d168",
"amount": "3192",
"maxTimeoutSeconds": 60
}
]Output schema
{
"bazaar": {
"info": {
"input": {
"body": {
"model": "llama3.2:3b",
"options": {
"num_predict": 64
},
"prompt": "Explain metered GPU compute in one sentence."
},
"bodyType": "json",
"method": "POST",
"type": "http"
},
"output": {
"example": {
"lease_id": 1047,
"model": "llama3.2:3b",
"response": "Metered GPU compute bills by the second and settles onchain.",
"usage": {
"completion_tokens": 14,
"duration_ms": 640,
"prompt_tokens": 12
}
},
"type": "json"
}
},
"schema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"additionalProperties": false,
"properties": {
"body": {
"properties": {
"model": {
"description": "Which model answers.",
"enum": [
"llama3.2:3b",
"llama3.1:8b"
],
"type": "string"
},
"options": {
"description": "Generation options. The price scales with the output cap.",
"properties": {
"num_predict": {
"description": "Maximum output tokens. Lower is cheaper.",
"maximum": 1024,
"minimum": 1,
"type": "integer"
}
},
"type": "object"
},
"prompt": {
"description": "The prompt, up to 32 KiB.",
"minLength": 1,
"type": "string"
}
},
"required": [
"model",
"prompt"
],
"type": "object"
},
"bodyType": {
"enum": [
"json",
"form-data",
"text"
],
"type": "string"
},
"method": {
"enum": [
"POST",
"PUT",
"PATCH"
],
"type": "string"
},
"type": {
"const": "http",
"type": "string"
}
},
"required": [
"type",
"method",
"bodyType",
"body"
],
"type": "object"
},
"output": {
"properties": {
"example": {
"properties": {
"lease_id": {
"description": "The GPU lease that served it.",
"type": [
"integer",
"null"
]
},
"model": {
"type": "string"
},
"response": {
"description": "The generated text.",
"type": "string"
},
"usage": {
"properties": {
"completion_tokens": {
"type": [
"integer",
"null"
]
},
"duration_ms": {
"type": [
"integer",
"null"
]
},
"prompt_tokens": {
"type": [
"integer",
"null"
]
}
},
"type": "object"
}
},
"required": [
"model",
"response"
],
"type": "object"
},
"type": {
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
}
},
"required": [
"input"
],
"type": "object"
}
}
}Use it
curl
curl "https://api.prismnetwork.tech/inference/v1/inference" # -> 402 Payment Required, accepts[] lists how to pay # retry with a PAYMENT-SIGNATURE (or PAYMENT header) once paid
JavaScript
const res = await fetch("https://api.prismnetwork.tech/inference/v1/inference");
if (res.status === 402) {
const { accepts } = await res.json();
// pay one of accepts[] via an x402 client, then retry with the payment header
}Python
import httpx
res = httpx.get("https://api.prismnetwork.tech/inference/v1/inference")
if res.status_code == 402:
accepts = res.json()["accepts"]
# pay one of accepts[] via an x402 client, then retry with the payment headerMachine-readable
Everything on this page is also available as clean JSON at /resources/12996.json, and this resource appears in /discovery/resources and /discovery/search.