Start here

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

How it works

Everything Trellis does, and where it stops.

The routes, the receipts, the balance, the agent rulebook, the host network and the privacy routes, with the limits of each.

Find your next step

What do you want to do?

4

Budget caps per request, hour, day and week.

Agent rulebook
15min

Single-use ask-first approval window on /agents.

Owner approval
0USDC

Deposit required to host. Hosts join by hardware attestation and probation.

Network hosts
7days

Validity of a router-signed track-record certificate with a fresh pseudonym.

Certificates
Features / what a route tells you

Everything a call should come with.

Routing, payments, proof and privacy in one layer. Keep your SDK; get a receipt, a budget and a choice of how to pay.

01
Trellis

The open routing layer

Any model, any provider, any route. One familiar API for your next generation of agents. Know where every call goes and what it costs, down to the receipt.

02
Open API

Familiar request shapes

Keep the clients and request shapes your team already knows. Change the base URL and key, with OpenRouter-compatible routing preferences built in.

03
Prepaid credits

Prepaid, with a 0% router fee

One balance for every model and provider. Fund it with USDC on Solana from your own wallet.

04
Signed receipts

Portable proof per call

See the model, provider, tokens and cost behind each generation. A signed receipt travels with the response, and anyone can check it on /verify.

05
Agent payments

HTTP 402, built for agents

A request can begin without an account. Receive a 402 quote, pay, then retry with a payment proof.

06
Agent rulebook

Rules before every request

Cap spending per request, hour, day and week. Choose models, lanes, tools and working hours. Ask first, or stop the agent before its next request. Manage your agents.

07
Agent profiles

Choose what to publish

Opt in to public profiles with random slugs, an owner-chosen rulebook summary and the latest valid certificate. A2A-style cards and an MCP directory support discovery. Browse the directory or read profile limits.

08
Sealed agent hosting

Available for owner-built agents

Build and publish your agent sidecar image with the sealed recipe. The router verifies a registered agent’s TDX quote. No sealed agent is registered at trellis.example yet. Read the hosting limits.

09
Telegram approvals

Approve where you receive alerts

Link Telegram from /agents with a one-time code. Approve or deny the same single-use requests and receive alerts through Trellis’s bot. Approval details pass through Telegram. Link your account.

10
Encrypted chat

Encrypt on your device

End-to-end encrypted chat runs through the attested gateway. The router forwards ciphertext on this path. Other requests are read in memory to route them. Read how it works.

12
Fallback routing

Keep the request moving

Filter by price, latency, quantization and data policy. Unhealthy providers leave the pool, with fallbacks built in.

13
Open telemetry

Your usage, your tools

Keep usage visible across your existing systems with OpenTelemetry export and usage records.

14
Agent track record

Receipts you can inspect

Per-agent ledgers export signed receipts as CSV or JSON. Router-signed certificates use a fresh pseudonym and last seven days. They are verifiable, not anonymous.

15
Team controls

Built for shared work

Roles, budgets and access for the people building with you: one routing layer for a shared workspace.

Route types

One API.
Every kind of route.

The same request shape reaches a standard model, an attested host or a Stock Token payment. Encrypted chat uses on-device encryption through the attested gateway; ordinary requests are read in memory by the router.

The same request shape reaches a standard model or an attested host. Requests are read in memory by the router to route them.

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
How it works

Three steps.
No new SDK.

Point your client at the router, keep your code, and every call comes back with the route it took and the proof of what it cost.

STEP 01

Choose your model.

Use the familiar API request shape. Set your model, provider preferences and budget.

model · provider{} · budget
STEP 02

Let Trellis find the route.

The router filters providers by health, price, data policy and your requirements, with fallbacks ready.

1/price² × uptime × quality
STEP 03

Receive a receipt.

Every generation returns itemized usage, cost and a signed receipt you can check on /verify.

ed25519 · sha-256 · /verify
Accountability / Trellis Network

A public record for every host.

The Trellis Network is open for early hosts running the approved build. Admission checks the hardware and policy before a host serves requests.

Approved builds

Early hosts run the approved Intel TDX build in a supported confidential VM. Join with one command using join.mjs.

Automatic admission

Fresh quote, signed host policy v1 in the key log, and sanctions screening of operator and payout addresses. New hosts start on probation with a public record.

Check the approved build and join · Inspect host records

Host admission · processIntel TDX · approved build
01buildapproved recipeIntel TDX
02quotefresh hardware evidenceattestation
03policysigned host policy v1key log
04screenoperator + payout addressesadmission
05joinnew host probationpublic record
Deposit requiredNone
PayoutsNot switched on yet
01Quote
02Policy
03Screening
04Probation
Gateway / controls per key

Batteries included. All removable.

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    }  }}

Privacy / attested routes

Privacy with a receipt.

A private request goes only to a provider whose TEE evidence was verified minutes ago. If the evidence is missing or stale, the request fails closed.

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
Roadmap / live and next

A clear route forward.

Encrypted chat, the agent rulebook and early-host admission are live at trellis.example. Sealed agent hosting is available, but no sealed agent is registered at trellis.example yet. Network host payouts and bond slashing are not switched on yet.

This router runs the core launch surface: chat, the model catalogue, API keys, prepaid credits, x402 per call and signed receipts. The areas below are built, and each card says whether this router has it enabled.

01LiveSigned receipts only on this router

Encrypted chat and GRAFT

On-device encryption through the attested gateway, signed receipts, key transparency and per-host receipt anchoring.

02LiveNot enabled on this router

The agent rulebook

Budgets, rules, approvals on /agents and Telegram, receipts, alerts, circuit breakers, progressive autonomy, certificates and opt-in profiles.

03LiveNot enabled on this router

Trellis Network

Open for early hosts on the approved Intel TDX build, automatic admission, probation, public host records and live network statistics.

04LiveChat only on this router

Files and payments

Private RAG/files, PDF support, Chat, Tor onion access and blind tokens.

Agreements between agents are live: escrow and dispute contracts on Solana, with disputes ruled by a jury of models on attested hardware.

Agent wallets with on-chain rules; GPU hosts on the network; network payouts.Next
About Trellis

Every open model.
A route you can check.

Trellis is an open inference router for Solana. A familiar API is the starting point. Clear payments, provider accountability and portable receipts are the reason to go further.

A route should tell you more than whether a request succeeded.

Which provider served it? What did it cost? What evidence supports its privacy claims? Who gets paid? Routing, USDC settlement, signed receipts and attestation checks run in the router, with contracts on Solana.

Built for developers

A familiar shape.
A different route.

Keep your existing request shape. Point your client at your router’s /api/v1 and use a Trellis key. Streaming, tools, structured output and provider preferences work as you expect.

Quickstart · node
// Change two lines: the base URL and the key.
const client = new OpenAI({
  baseURL: process.env.TRELLIS_BASE_URL, // "<your router>/api/v1"
  apiKey: process.env.TRELLIS_API_KEY,   // "sk-tr-v1-…"
});

const generation = await client.chat.completions.create({
  model: "meta-llama/llama-3.3-70b-instruct",
  messages: [{ role: "user", content: "Hello, Trellis." }],
});