createProvider.md
Create a Provider
Creates a new named provider. Either supply a connection_id to share an existing credential, or supply api_key / credentials to create an inline secret as part of the request.
Pass models to enable a list of upstream model names as 1:1 routes in the same call — equivalent to creating each route individually afterwards.
A Provider is a named upstream that authenticates with one credential and serves a model family. Provider creation supports two modes:
- Inline credential — pass
api_key(orcredentials) directly. Barndoor stores the secret in its encrypted secret store, scoped to this provider. - Shared credential — pass
connection_idreferencing an existing Credential. The provider'sauth_type,base_url, and settings inherit from the shared record.
Auto-enabling models in one call
Pass a list of upstream model names in models and Barndoor will create a 1:1 Model Route for each one in the same call. The route's alias matches the upstream model name so callers can address it as <provider>/<model>. Add bare-name aliases or failover routes afterwards via the Model Routes endpoints.
Example
curl -X POST https://app.barndoor.ai/api/llm-gateway/admin/providers \
-H "Authorization: Bearer $BARNDOOR_JWT" \
-H "Content-Type: application/json" \
-d '{
"name": "OpenAI Production (US)",
"model_provider": "openai",
"base_url": "https://api.openai.com/v1",
"connection_id": "4f8b2a3c-12ee-4d92-9c7b-e7d2f8b0a111",
"models": ["gpt-4o-mini", "gpt-4o", "text-embedding-3-large"]
}'
OpenAPI
openapi: 3.1.0
info:
title: Barndoor LLM Gateway API
version: 1.0.0
description: >
REST API for the Barndoor LLM Gateway: configure providers, model routes,
pricing, governance, and operate a multi-provider LLM platform
programmatically.
All endpoints in this document are scoped to your organization. They are the
same APIs powering the Barndoor portal under **LLM Configuration**,
**LLM Controls**, and **Settings - My Models**, exposed for teams that
prefer scripting over the UI.
## Base URL
All requests are issued against your Barndoor instance:
```
https://app.barndoor.ai/api/llm-gateway
```
Replace `app.barndoor.ai` with your tenant host if you run on Enterprise.
## Authentication
Endpoints accept a JWT Bearer token issued by your Barndoor identity
provider. Tokens can be obtained interactively via the Barndoor SDK:
```ts
const sdk = await loginInteractive();
```
The token must be sent in the `Authorization` header on every request:
```
Authorization: Bearer eyJhbGciOi...
```
Note: the `bd-...` API keys you create through these endpoints are for
runtime LLM traffic (`/v1/chat/completions`, `/v1/messages`, etc.), not for
administrative calls. Administrative endpoints require a user/admin JWT.
## Permissions
Most endpoints require an `admin` (or higher) role on the calling user.
Read-only endpoints are typically accessible by all authenticated users.
Read-only listings under `/user/...` are scoped to the authenticated user.
## Errors
Errors are returned as JSON with a stable shape:
```json
{ "error": "BadRequest", "message": "request_timeout_secs must be between 1
and 3600" }
```
contact:
name: Barndoor Support
url: https://barndoor.ai
servers:
- url: https://{host}/api/llm-gateway
description: >-
Production / Trial (Barndoor SaaS). The gateway lives on your Barndoor
control-plane host. For Enterprise or self-hosted deployments, replace the
host with your portal hostname — the authoritative value is shown on
Settings → My Models in the portal.
variables:
host:
description: Your Barndoor control-plane (portal) hostname
default: app.barndoor.ai
- url: https://app.barndooruat.com/api/llm-gateway
description: UAT
- url: https://app.barndoordev.com/api/llm-gateway
description: Dev
security:
- BearerAuth: []
tags:
- name: Credentials
description: >-
Reusable upstream credentials (API keys, AWS roles, Vertex service
accounts)
- name: Providers
description: Named upstream providers backed by credentials and a model family
- name: Provider Catalog
description: Read-only catalog of supported upstream provider templates
- name: Model Routes
description: Map client-facing aliases to one or more upstream provider/model pairs
- name: Model Pricing
description: Per-million-token input/output costs for usage and budget reporting
- name: Rate Limits
description: Requests-per-minute and tokens-per-minute caps
- name: Token Budgets
description: Daily, weekly, or monthly token and cost ceilings
- name: Model Access
description: Allowlist or denylist policies for models, providers, or aliases
- name: Smart Models
description: Routing policies that pick a target model based on the request
- name: Governance Configuration
description: Org-wide behavior toggles for the LLM Gateway
- name: Route Health
description: Operational view of upstream route ejection and recovery
- name: API Keys
description: Org-managed gateway API keys (the `bd-...` keys callers send on `/v1/...`)
- name: User
description: Self-service endpoints for the authenticated user
paths:
/admin/providers:
post:
tags:
- Providers
summary: Create a provider
description: |
Creates a new named provider. Either supply a `connection_id` to share
an existing credential, or supply `api_key` / `credentials` to create
an inline secret as part of the request.
Pass `models` to enable a list of upstream model names as 1:1 routes
in the same call — equivalent to creating each route individually
afterwards.
operationId: createProvider
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/CreateProviderRequest'
responses:
'200':
description: The newly created provider
content:
application/json:
schema:
$ref: '#/components/schemas/Provider'
'400':
$ref: '#/components/responses/BadRequest'
components:
schemas:
CreateProviderRequest:
type: object
required:
- name
- model_provider
- base_url
properties:
name:
type: string
model_provider:
$ref: '#/components/schemas/ModelProviderSlug'
auth_type:
$ref: '#/components/schemas/AuthType'
base_url:
type: string
api_key:
type: string
format: password
description: Required for direct API-key auth when no `connection_id` is provided
catalog_id:
type: string
format: uuid
description: Optional reference to a provider catalog template
connection_id:
type: string
format: uuid
description: Optional reference to a shared Credentials record
models:
type: array
description: |
Upstream models to enable on this provider as 1:1 model routes.
Each entry creates a route where the alias equals the upstream model
name (so callers can address it as `<provider>/<model>`).
items:
type: string
example:
- gpt-4o-mini
- gpt-4o
settings:
type: object
additionalProperties: true
credentials:
type: object
description: Structured non-API-key credentials (AWS keys, Vertex SA JSON, etc.)
additionalProperties: true
request_timeout_secs:
type: integer
nullable: true
minimum: 1
maximum: 3600
stream_idle_timeout_secs:
type: integer
nullable: true
minimum: 1
maximum: 1800
Provider:
type: object
description: A named upstream provider backed by a credential and a model family.
required:
- id
- org_id
- name
- model_provider
- auth_type
- base_url
- enabled
- settings
- created_at
- updated_at
properties:
id:
type: string
format: uuid
org_id:
type: string
format: uuid
catalog_id:
type: string
format: uuid
nullable: true
description: Reference to a built-in provider catalog template, if used
connection_id:
type: string
format: uuid
nullable: true
description: Reference to a shared Credentials record, if any
name:
type: string
example: OpenAI Production (US)
model_provider:
$ref: '#/components/schemas/ModelProviderSlug'
auth_type:
$ref: '#/components/schemas/AuthType'
base_url:
type: string
format: uri
enabled:
type: boolean
default: true
settings:
type: object
additionalProperties: true
request_timeout_secs:
type: integer
nullable: true
minimum: 1
maximum: 3600
description: |
Provider-tier total-request timeout override. When `null` (the
default) the gateway inherits the platform default. Affects every
route served by this provider unless a more specific Model Route
value overrides it.
stream_idle_timeout_secs:
type: integer
nullable: true
minimum: 1
maximum: 1800
description: |
Maximum allowed idle gap between streamed response chunks. `null`
inherits the platform default.
catalog_slug:
type: string
nullable: true
description: Catalog slug shorthand used in some response listings
ModelProviderSlug:
type: string
description: Slug of the upstream model provider this resource speaks to
enum:
- openai
- anthropic
- azure_openai
- google_ai
- bedrock
- vertex
- groq
- together
- mistral
- cohere
- xai
- fireworks
- perplexity
- openrouter
- deepseek
- custom
example: openai
AuthType:
type: string
description: >
The authentication scheme this credential or provider uses to talk to
the upstream model provider. Valid values depend on `model_provider`:
for OpenAI/Anthropic-style vendors this is typically `api_key`; for AWS
Bedrock it is one of `aws_role`, `aws_keys`, or `bedrock_api_key`; for
Google Vertex it is `google_adc`, `google_service_account`, or
`google_impersonation`; Anthropic OAuth passthrough uses
`oauth_passthrough`.
example: api_key
Error:
type: object
required:
- error
- message
properties:
error:
type: string
description: A short machine-readable error code
example: BadRequest
message:
type: string
description: A human-readable description of what went wrong
example: request_timeout_secs must be between 1 and 3600
responses:
BadRequest:
description: The request body or query parameters were invalid
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
securitySchemes:
BearerAuth:
type: http
scheme: bearer
bearerFormat: JWT
description: |
JWT obtained through Barndoor's authentication flow. Pass the token
verbatim in `Authorization: Bearer <token>`. Use the Barndoor SDK's
`loginInteractive()` helper to obtain a token in scripts and notebooks.