---
title: "ai.inference-deployment@1 · OpenVibe.Services"
canonical: "https://openvibe.services/docs/contracts/ai.inference-deployment"
updated: null
---

# ai.inference-deployment@1 · OpenVibe.Services

HTML: [ai.inference-deployment@1 · OpenVibe.Services](https://openvibe.services/docs/contracts/ai.inference-deployment)

# AiInferenceDeployment `ai.inference-deployment@1`

Generated at 2026-11-13 06:25:48 UTC from [`openvibe-contracts v0.419.0`](https://github.com/OpenVibers/OpenVibe.Contracts/tree/v0.419.0) and [`openvibe-sdk v0.161.0`](https://github.com/OpenVibers/OpenVibe.SDK/tree/v0.161.0).

- Version: 1.0.0
- Owner: ai
- Visibility: first-party
- Status: active
- Compatibility: backward
- Schema: [`https://openvibe.network/contracts/ai/inference-deployment.v1.json`](/docs/contracts/ai.inference-deployment.json)

ai.inference-deployment@1: a loaded inference deployment for a pinned artifact. Describes where it runs, its trust tier, commercial rights, health, limits and the rate card that prices its supply cost.

## Fields

| Field | Type | Required | Description | Constraints |
| --- | --- | --- | --- | --- |
| `id` | string | yes | Deployment id, unique within OpenVibe.AI. | - `maxLength 256` |
| `artifact_id` | string | yes | Exact artifact id this deployment loads. | - `pattern ^[a-zA-Z0-9._-]+/[a-zA-Z0-9._-]+(:[a-zA-Z0-9._-]+)?@[a-zA-Z0-9._-]+$`<br>- `maxLength 256` |
| `region` | string | yes | Deployment region or residency label. |  |
| `trust_tier` | enum |  | Who operates the deployment and what data may reach it. | - `one of "first_party", "owner_node", "approved_wholesale", "unverified"` |
| `operator` | string |  | Operator slug or \`owner:<subject\_id>\` for a private machine. |  |
| `host` | string \| null |  | Internal host identifier; never exposed to untrusted callers. |  |
| `endpoint` | string \| null |  | Service endpoint for this deployment (internal or partner). | - `format uri` |
| `status` | enum | yes | Current load/health state. | - `one of "warming", "ready", "full", "degraded", "offline"` |
| `loaded_at` | string \| null |  |  | - `format date-time` |
| `limits` | object |  |  | - `no other fields` |
| `limits.max_concurrency` | integer |  |  | - `minimum 1` |
| `limits.context_tokens` | integer |  |  | - `minimum 1` |
| `limits.max_output_tokens` | integer |  |  | - `minimum 1` |
| `supply_rate_card_id` | string \| null |  | Reference to the supply rate card (platform.rate-card@1) that prices this deployment. |  |
| `provider_access` | enum |  | Commercial eligibility for paid managed routes. | - `one of "OWN_DEPLOYMENT", "AUTHORIZED_WHOLESALE", "CUSTOMER_BYOK", "RESTRICTED", "UNVERIFIED"` |
| `commercial_rights` | enum |  | Resale authority recorded for this deployment. | - `one of "OWN_DEPLOYMENT", "AUTHORIZED_WHOLESALE", "CUSTOMER_BYOK", "RESTRICTED", "UNVERIFIED"` |
| `privacy_policy` | string \| null |  | Retention/zero-retention policy label. |  |
| `health` | object |  |  | - `no other fields` |
| `health.healthy` | boolean |  |  |  |
| `health.last_check_at` | string \| null |  |  | - `format date-time` |
| `health.reason` | string \| null |  |  |  |
| `updated_at` | string |  |  | - `format date-time` |

## Examples

From the contract's own test fixtures: valid ones validate, rejected ones must fail.

 Valid: owned-gpu

~~~~
{
  "id": "dep-qwen-9b-us-east-001",
  "artifact_id": "qwen/qwen3-9b-abliterated:q4_k_m@3f2a1c9",
  "region": "us-east",
  "trust_tier": "first_party",
  "operator": "openvibe",
  "host": "gpu-001.internal",
  "endpoint": "http://127.0.0.1:4800/v1",
  "status": "ready",
  "loaded_at": "2026-11-03T00:00:00.000Z",
  "limits": {
    "max_concurrency": 16,
    "context_tokens": 32768,
    "max_output_tokens": 8192
  },
  "supply_rate_card_id": "rc-qwen-owned-001",
  "provider_access": "OWN_DEPLOYMENT",
  "commercial_rights": "OWN_DEPLOYMENT",
  "privacy_policy": "zero_retention",
  "health": {
    "healthy": true,
    "last_check_at": "2026-11-03T00:00:00.000Z",
    "reason": null
  },
  "updated_at": "2026-11-03T00:00:00.000Z"
}
~~~~

Valid: wholesale

~~~~
{
  "id": "dep-deepinfra-llama-8b",
  "artifact_id": "meta-llama/llama_3.1_8b_instruct:fp16@bca2580",
  "region": "us-west",
  "trust_tier": "approved_wholesale",
  "operator": "deepinfra",
  "endpoint": "https://api.deepinfra.com/v1/openai",
  "status": "ready",
  "loaded_at": "2026-11-03T00:00:00.000Z",
  "limits": {
    "max_concurrency": 100,
    "context_tokens": 131072,
    "max_output_tokens": 4096
  },
  "supply_rate_card_id": "rc-deepinfra-llama-8b-001",
  "provider_access": "AUTHORIZED_WHOLESALE",
  "commercial_rights": "AUTHORIZED_WHOLESALE",
  "privacy_policy": null,
  "health": {
    "healthy": true,
    "last_check_at": "2026-11-03T00:00:00.000Z",
    "reason": null
  },
  "updated_at": "2026-11-03T00:00:00.000Z"
}
~~~~

Rejected: bad-access

~~~~
{
  "id": "dep-bad-access",
  "artifact_id": "qwen/qwen3-9b-abliterated:q4_k_m@3f2a1c9",
  "region": "us-east",
  "status": "ready",
  "provider_access": "FREE"
}
~~~~

Rejected: bad-trust-tier

~~~~
{
  "id": "dep-bad-trust",
  "artifact_id": "qwen/qwen3-9b-abliterated:q4_k_m@3f2a1c9",
  "region": "us-east",
  "trust_tier": "hostile",
  "status": "ready"
}
~~~~

Rejected: missing-artifact

~~~~
{
  "id": "dep-no-artifact",
  "region": "us-east",
  "status": "ready"
}
~~~~

## Validate

~~~~
const contracts = require('openvibe-contracts');
contracts.validate('ai.inference-deployment@1', value);   // { valid, errors: [{ path, message }] }
~~~~