Start here

↑ ↓ to choose · Enter to open · Esc to close

How a call works

Trellis routes a model request, quotes the payment in USDC and signs a record of the call.

  1. Choose a route

    Start with a model ID. The router considers eligible endpoints and the routing preferences in your request.

    Model catalog
  2. Approve the quote

    An unpaid request returns HTTP 402. Review the network, recipient and amount before your wallet signs.

    Request a quote
  3. Check the receipt

    Use the receipt ID to check the router’s signature. An inclusion proof can tie the record to its hourly batch.

    Receipt verifier

Routing examples

The launch catalog serves public routes. Check the model’s available endpoints before requesting attestation.

chat/completions
const res = await client.chat.completions.create({
  model: "meta-llama/llama-3.3-70b-instruct",
  messages,
  provider: { sort: "price", allow_fallbacks: true },
});

res.provider;        // who served it
res.usage.cost;      // what it cost, in USDC
res.receipt.sig;     // Ed25519 signature
Filterhealth, price, data policy
Routebest provider, fallbacks ready
Receiptsigned, itemized, anchored
What the router and provider can see

Attestation checks

On the public route, the router and the inference provider can read the request. The example shows the additional checks a route requiring fresh attestation would perform.

End-to-end encrypted chat

The client encrypts on your device; the attested gateway handles inference while the router forwards ciphertext.

Other request paths

Trellis’s router reads request text in memory to route it. Attested serving alone does not hide prompts from the router.

Evidence and stored records

Inspect signed receipts, the key transparency log and the data inventory. Receipts store hashes, token counts and cost, not prompt or answer text.

Check what the router has verified about any provider · Encrypted chat · What we keep

Private route · examplefail-closed
Request :private
Quote verified
Route selected
Receipt signed
request
llama-3.3-70b:private
tee
intel tdx + nvidia cc
nonce
5e2a…c91d · bound
quote
sha256:9c41e0b2…a1f307e2
freshness
attested 4 min ago
router
reads ordinary requests in memory
receipt
attestation sha256:9c41e0b2…a1f307e2
Attestation verified · route allowed
Explore agent key settings

Key configuration

Set boundaries on the key and attach an agent rulebook. Trellis’s router enforces it for requests through Trellis only.

Bring your own workflow

Keep your SDK, choose providers and configure fallbacks. Cache and guardrails are opt-in.

Budget, rules and a stop switch

Set request/hour/day/week caps, models, lanes, tools and working hours. Stop refuses the next request; the owner resumes.

Ask first, then inspect

Approve once on /agents within 15 minutes. Read signed receipts in the per-agent ledger and export CSV or JSON.

Alerts, breakers and autonomy

Follow the /agents alert feed, spend-alert webhook or Telegram via Trellis’s bot. Circuit breakers and progressive autonomy support spending caps up to 10x.

Open the agent rulebook · Read the API and MCP tools

POST /api/v1/keys · example4 / 7 on
{  "name": "support-agent",  "limit": 250,  "limit_reset": "monthly",  "rpm": 600,  "tpm": 400000,  "allowed_models": ["qwen/qwen3-32b", "deepseek/deepseek-r1"],  "team": null,  "pay_with_default": null,  "expires_at": null,  "guardrails": null,  "routing": {    "provider": {      "sort": "latency",      "allow_fallbacks": true    }  }}

Browse tools by task
Find your next step

What do you want to do?