Open inference, one compatible API

The inference marketplace built for agents.

Route OpenAI- and Anthropic-compatible requests to the best-priced available provider, with transparent centralized fallback. Pay by card, USDC balance, or per request with x402.

Have GPUs or unused API capacity? Become a provider →

Open-weight models
Commercial providers
Private routes
Best-price routing
UsePod Marketplace
9 providers online
Find the best route
⌘ K
ProviderInput / MOutput / MLatency
Best route selectedMarketplace route · OpenAI-compatible response
Save 60%
OpenAI + Anthropic compatibleMarketplace + commercial routesCard, USDC, or x402
Marketplace

Same models. Competing prices.

Every open-weight model on UsePod is served by multiple providers — independent marketplace operators and commercial APIs — competing on price and latency. You see all of them before a single token is billed.

ModelMarketplace fromCommercial fromRoutes online
GPGPT OSS 120B131k context · open weights
$0.024 / $0.12input / output per M$0.09 / $0.453 marketplace · 4 commercial
QWQwen 3.5 397B262k context · open weights
$0.19 / $0.78input / output per M$0.45 / $1.802 marketplace · 5 commercial
DSDeepSeek V3.2128k context · open weights
$0.20 / $0.40input / output per M$0.27 / $1.102 marketplace · 6 commercial
L4Llama 4 Maverick1M context · open weights
$0.15 / $0.60input / output per M$0.22 / $0.853 marketplace · 5 commercial
MSMistral Small 4128k context · open weights
$0.05 / $0.15input / output per M$0.10 / $0.302 marketplace · 3 commercial
GLGLM-5.1200k context · open weights
$0.35 / $1.40input / output per M$0.60 / $2.201 marketplace · 4 commercial
Snapshot for illustration — live prices, providers, and latency in the app.Open the full marketplace →
How it works

Choose. Constrain. Call.

UsePod sits between your agent and every provider that can serve its request. You describe what an acceptable route looks like — the router does the rest, on every call.

01 — CHOOSE

Pick a model

Browse open-weight models served by marketplace operators, alongside commercial providers. Compare price, context, and live availability before you commit.

{
  "model": "deepseek-v4-flash",
  "messages": [
    { "role": "user", "content": "Hello" }
  ]
}
02 — CONSTRAIN

Set the policy every route must meet

Set price ceilings and choose whether routing may fall back to centralized providers. The router enforces these headers on every request.

X-Pod-Max-Price-Input: 400000
X-Pod-Max-Price-Output: 600000
X-Pod-Routing-Mode: marketplace-only
03 — CALL

Send the request you already send

Same OpenAI or Anthropic request shape, same streaming, same tool calls. The response identifies the route and provider that served it.

X-Pod-Route: marketplace
X-Pod-Provider-Id: <provider-uuid>
X-Balance-Cost-Microunits: 114
Why UsePod

A market, not a walled garden.

Open-weight models close the gap with frontier releases every quarter. When any provider can serve the same model, price converges on marginal cost — UsePod is where that convergence happens.

Real price discovery

Providers compete on identical, content-addressed model weights. You see every route's price before it serves a token, and pay the marginal cost of compute — not a brand premium or subscription tier.

Privacy as a routing constraintTEE soon

Choose which route types may serve each request — marketplace-only, no-retention, region-pinned. Hardware-attested private inference via TEE enclaves is shipping next on the roadmap.

One compatible API

OpenAI and Anthropic request shapes, streaming, and tool calls — served from a single endpoint. Migrating an existing agent is a base-URL swap, not a rewrite.

Fallback that is never silent

If no marketplace route meets your policy, UsePod can fall back to commercial providers you've allowed — and says so in the response metadata. You always know who served the request and why.

Security & verification

What's live, and what's next.

Trust claims should be checkable. Here is exactly where the stack stands: routing controls and cost transparency are live today; the hardware-enforced privacy layer is in active development and marked accordingly.

The goal is inference where privacy is proven by attestation, not promised by policy.

Intel TDXAMD SEV-SNPAWS NitroNVIDIA CCX25519 + ChaCha20-Poly1305
Route policy enforcementPrice ceilings, allowed route types, regions, and explicit fallback — enforced by the router on every request.
Live
Per-request receiptsEvery response discloses the serving provider, route type, and exact cost. No silent rerouting, ever.
Live
No-retention marketplace routesMarketplace routes that don't store prompts or completions, selectable per request as a routing constraint.
Live
TEE inference with remote attestationDecryption and inference inside a hardware enclave. Attestation proves the exact model and code path — the operator sees nothing.
Soon
Client-side payload encryptionPrompts encrypted in your runtime before they leave it; plaintext never traverses the network or the router.
Soon
Content-addressed model weightsWeights cryptographically hashed and pinned in attestation, so a node cannot serve a modified variant.
Soon
Developers

Two lines to migrate.

UsePod speaks the API your agent already speaks. Point your existing SDK at the endpoint and every request becomes a marketplace request — routing, fallback, and payment handled underneath.

  • OpenAI and Anthropic compatible — same shapes, streaming, and tool calls
  • Routing policy per request or per key: price, latency, route types, fallback
  • Pay by card or USDC balance — or fully agent-native, per request, with x402
  • LangChain, LlamaIndex, and CrewAI integrations
OpenAI-compatibleagent.ts — point your SDK at UsePod
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.usepod.ai/v1",  // line 1
  apiKey: process.env.USEPOD_API_KEY,   // line 2
});

const completion = await client.chat.completions.create({
  model: "deepseek-v3.2",
  messages,
  usepod: {                             // optional policy
    max_input_price: 0.25,
    routes: ["marketplace", "commercial"],
    fallback: "explicit",
  },
});
agent-nativex402 — no account, no API key
// An agent with a funded wallet pays per request:
// 1. Request hits a 402 paywall with a payment spec
// 2. SDK signs a USDC micro-payment from the wallet
// 3. Retries with the X-Payment header — <500ms round trip
import { PodClient } from "@usepod/sdk";

const client = new PodClient({ wallet: agentWallet });
For institutions

Controls your procurement team will ask about.

Agents spend autonomously; organizations still need governance. UsePod gives both sides what they need — deterministic limits for the machines, visibility and predictable billing for the humans.

SPEND

Programmatic spending limits

Per-key, per-team, and per-agent budgets enforced deterministically — no inference required to decide whether to spend.

GOVERN

Route governance

Org-wide policies for allowed providers, route types, regions, and retention — applied before any developer's request leaves the router.

AUDIT

Usage & audit exports

Per-request receipts roll up into exportable usage records: model, route, provider, and cost for every call your fleet makes.

PAY

Billing that fits procurement

Card and invoiced billing for organizations, USDC balances for treasuries, x402 for fully autonomous agents — on one account.

For providers

Turn idle capacity into a route.

Have GPUs — or unused API quota? Serve the marketplace at your price.

Any operator can list open-weight models at a price they set. Demand routes to you whenever you're the best match for a request's policy. Payouts settle in USDC per request served — operators keep 90% of every inference fee.

Today, trust is contractual and monitored. With TEE attestation, it becomes cryptographic: clients verify your node runs unmodified code, and reputation stops mattering.

Become a provider
1
Bring capacitySelf-hosted GPUs running open-weight models, or resell headroom on commercial API quota you already pay for.
2
Set your priceYou choose the per-token rate for each model you serve. The market decides if it routes to you.
3
Serve requestsThe router sends you traffic that matches your price, latency, and policy profile — no marketing, no sales.
4
Get paid per requestUSDC settlement on Solana for every request served. 90% of the fee is yours.
The protocol

The future of software is agent-first.

The infrastructure that serves it must be built to a different standard: private by hardware, sovereign by design, machine-speed by necessity. That is where UsePod is headed — a permissionless inference protocol where payment, privacy, and verification are properties of the network, not promises of a company.

“A privacy policy is a legal instrument, enforced after the fact — if at all. There must be a separation of mind and state: an agent's reasoning isolated not by policy, but by mathematics and hardware.”
~$0.00025per settlement on Solana — the only chain where per-inference micro-payments are rational at scale.
~400 msto finality. An agent pays, gets its completion, and moves on — inside a single reasoning step.
x402 + MPPper-call paywalls and session-based bulk settlement, so agents pay as they go with no human in the loop.
<500 mspayment round trip: parse the 402, sign from the harness wallet, retry with the payment header.