prism. · GPU compute your agents can rent with a wallet
https://api.prismnetwork.tech/inference/v1/batchGPU compute your agents can rent with a wallet. Lease NVIDIA capacity, pay per second in USDG, and settle every lease onchain with a public receipt.
Paid verification
How it worksNo sponsored paid call yet.
Pay this endpoint once from your own wallet (Base USDC, up to $1.00) and we call it and record what came back. Your wallet pays the listed recipient directly; Agent Tools never holds funds. Sponsored checks prove delivery; they do not count as demand.
Quality grade
How grading works- ✓ Answers a real HTTP 402 challenge
- ✓ Publishes a /.well-known/x402 descriptor
- ✓ Payment address on record
- ✓ Settlement network declared
- ✓ Price declared
x402 readiness
Readiness is how fully this listing follows its protocol and how it behaved in our probes over 30 days. It is shown for reference and does not move it in search. Search order and leaderboards use the separate quality grade (here B, 69.0/100), which weighs availability, payability and on-chain demand. How the two differ
| Valid payment requirements | 10/10 | Payment requirements carry a payee, a mainnet network and a price. |
| Live 402 challenge | 25/25 | Paid endpoint answers with an HTTP 402 challenge (812 ms). |
| x402 version | n/a | x402 version not observed yet. |
| Signed descriptor | n/a | No x402 standard defines a signed descriptor. |
| Uptime (30 days) | 15/15 | 32/32 probes succeeded over 30 days (100%). |
| Resource declaration | 10/10 | Declares 8 paid resource(s). |
| Verified identity | 5/10 | Publisher descriptor (/.well-known/x402 or OpenAPI) on record; claim this listing to verify domain control. |
| Freshness + modern flags | 5/5 | seen in a source within 7 days; declares x402. |
| Security declaration | n/a | Payment is the access control for an x402 resource. |
Compared with peers
Against 10,060 reachable x402 APIs in our daily snapshot (2026-11-12 01:39 UTC). Display only; it does not change search order.
- Readiness
- Higher than 94% of peers
- This listing 93 · peer median 78
- Latency
- Faster than 8% of peers
- This listing 812 ms · peer median 205 ms
Where it loses the most points, and how to win them back
- Verified identity −5
— Claim the listing and prove control of its domain.
Now: Publisher descriptor (/.well-known/x402 or OpenAPI) on record; claim this listing to verify domain control.
Paid endpoints
8 resource(s) advertised by this origin. Each price below is that resource's own x402 price; the headline price is the range across them.
https://api.prismnetwork.tech/inference/v1/inference
$0.0121 / call
One LLM generation. The price is the model's base plus its per-token rate over the requested output cap, and the unpaid 402 quotes the exact figure for every network it accepts. On Base, sign an EIP-3009 authorization for the quoted USDC amount and send it in the payment header; you need no gas, bec
https://api.prismnetwork.tech/inference/v1/batch
$0.0121 / call
Many independent prompts in one paid call. The price is the single-request price times the number of prompts, and the unpaid 402 quotes the exact figure. Each prompt runs whole on one rented GPU, and the gateway spreads them over every GPU it holds, so a batch finishes in roughly the time the slowes
https://api.prismnetwork.tech/inference/v1/chat/completions
$0.1329 / call
One chat completion served inside a Phala GPU TEE, in the OpenAI request and response shape. The price is the model's base plus its per-token rate over the max_tokens you ask for, and the unpaid 402 quotes the exact figure. The gateway forwards your request bytes unchanged and returns the upstream b
https://api.prismnetwork.tech/inference/v1/attestation
The TEE's attestation report for a caller-chosen nonce of 64 lowercase hex characters: the TDX quote, the measured compose, and the workload keyset the receipt signing keys and encryption keys are drawn from. Free.
https://api.prismnetwork.tech/inference/v1/receipts/{id}
The signed receipt for one completion, by the id its response carried. It binds the hash of the request bytes the enclave received, the hash of the response bytes it returned, and the upstream GPU verification outcome. Fetch it promptly; upstream retention is short. Free.
https://api.prismnetwork.tech/inference/v1/sessions
The attested upstream sessions currently serving, with the evidence each receipt cites. Add {id} to the path for one session's full record. Free.
https://api.prismnetwork.tech/inference/v1/gpu-evidence
The GPU attestation evidence for a model, in the shape NVIDIA's remote attestation service takes as a request body, so a caller can have the GPU leg verified by NVIDIA directly rather than by us. Free.
https://api.prismnetwork.tech/inference/v1/models
Models, per-model pricing, and the gateway's current state. Free.
How to call
curl -sS -i -X POST https://api.prismnetwork.tech/inference/v1/batch # expect HTTP 402 Payment Required (about $0.012144/call)Listed in
Directories this entry was found in.