Auxen Deployments API
The Deployments API from Auxen — 8 operation(s) for deployments.
Work with this as data
Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/auxen-ai:auxen-ai-deployments-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
OpenAPI Specification
openapi: 3.2.0
info:
title: Auxen Headless Deployments API
version: 1.3.0
description: 'Programmatic API for Auxen: hire and manage AI workers (`/v1/workers`,
`/v1/connections`, approvals; also over MCP and A2A), and deploy and
manage private open-weight model endpoints. Anything a human can do in
the dashboard, an agent can do via this API.
**Two key types:**
- `auxen_live_…` / `auxen_test_…` — your account-level **agent management**
key. Authorizes deploying, switching models, and billing operations.
- `auxk_…` — a per-deployment **inference** key returned in the `api_key`
field of every deployment object. Authorizes inference calls on that
deployment only. Hand it to downstream services without giving up
management rights.
**Billing:**
All Auxen deployments are billed **pay-as-you-go** from a prepaid USD credit
balance, per minute of active time; billing stops when a deployment is
paused or deleted. Throughput levels (Standard, Double, Quad, Max)
increase simultaneous request handling at the same model quality. Top up
the balance with `POST /v1/billing/add-credits`.
**2026 renames:** `/v1/provision` → `/v1/deploy`, `/v1/instances` →
`/v1/deployments`, `/scale` → `/throughput`, `/wake` → `/resume`.
Old routes keep working until 2027-04-02 and send `Deprecation`,
`Sunset`, and `Link` headers. Responses carry new and old field names
side by side (`deployment_id` + `instance_id`, `throughput` +
`capacity`, `rate_per_hour` + `hourly_rate`, `ready_estimate` +
`estimated_ready_at`). Migration guide: https://auxen.ai/docs/api/migration'
contact:
email: hello@auxen.ai
url: https://auxen.ai/contact
servers:
- url: https://api.auxen.ai
description: Production
tags:
- name: Deployments
paths:
/v1/deploy:
post:
summary: Deploy a model
description: 'Returns immediately with `status: deploying`. Poll `GET /v1/deployments/{deploymentId}` until `status: ready`, then use the returned `endpoint` + `api_key` for inference.'
tags:
- Deployments
security:
- AgentKey: []
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- model
properties:
model:
type: string
description: Model ID from GET /v1/models
example: qwen3.5-9b
throughput:
oneOf:
- enum:
- standard
- double
- quad
- max
- type: integer
enum:
- 1
- 2
- 4
- 8
description: Throughput level. More throughput handles more simultaneous requests at the same answer quality. Double, Quad, and Max cost 1.9×, 3.75×, and 7.5× the Standard rate. Numbers 1/2/4/8 are accepted as aliases.
default: standard
capacity:
type: integer
enum:
- 1
- 2
- 4
- 8
deprecated: true
description: Deprecated alias of `throughput`; returned until 2027-04-02.
billing:
enum:
- pay_as_you_go
- on_demand
default: pay_as_you_go
description: Optional. `on_demand` is a back-compat alias for `pay_as_you_go`.
label:
type: string
maxLength: 120
webhook_url:
type: string
format: uri
description: URL Auxen POSTs this deployment's lifecycle events to.
responses:
'202':
description: Accepted — deployment started.
content:
application/json:
schema:
type: object
properties:
success:
type: boolean
const: true
data:
type: object
properties:
deployment_id:
type: string
example: inst_xxxxxxxxxxxx
instance_id:
type: string
deprecated: true
description: Deprecated alias of `deployment_id`; returned until 2027-04-02.
status:
const: deploying
legacy_status:
const: provisioning
model:
type: string
billing:
const: pay_as_you_go
throughput:
enum:
- standard
- double
- quad
- max
throughput_multiplier:
type: integer
enum:
- 1
- 2
- 4
- 8
capacity:
type: integer
deprecated: true
description: Deprecated alias of `throughput_multiplier`; returned until 2027-04-02.
rate_per_hour:
type: string
example: $0.20/hour
hourly_rate:
type: number
deprecated: true
description: Deprecated alias of `rate_per_hour`; returned until 2027-04-02.
ready_estimate:
type: string
format: date-time
estimated_ready_at:
type: string
format: date-time
deprecated: true
description: Deprecated alias of `ready_estimate`; returned until 2027-04-02.
polling_url:
type: string
format: uri
meta:
$ref: '#/components/schemas/Meta'
required:
- success
- data
- meta
'400':
description: Validation failure (missing model, bad throughput).
'402':
description: Insufficient credits.
operationId: postV1Deploy
x-operation-id-source: derived
/v1/deployments:
get:
summary: List your deployments
tags:
- Deployments
security:
- AgentKey: []
parameters:
- name: status
in: query
schema:
enum:
- deploying
- ready
- paused
- warming
- switching
- suspended
- error
- deleted
description: Pre-2026 status values are also accepted.
- name: billing
in: query
schema:
enum:
- subscription
- pay_as_you_go
- on_demand
- name: limit
in: query
schema:
type: integer
minimum: 1
maximum: 100
default: 20
responses:
'200':
description: OK
content:
application/json:
schema:
type: object
properties:
success:
type: boolean
const: true
data:
type: object
properties:
deployments:
type: array
items:
$ref: '#/components/schemas/Deployment'
instances:
type: array
items:
$ref: '#/components/schemas/Deployment'
deprecated: true
description: Deprecated alias of `deployments`; returned until 2027-04-02.
meta:
$ref: '#/components/schemas/Meta'
required:
- success
- data
- meta
operationId: getV1Deployments
x-operation-id-source: derived
/v1/deployments/{deploymentId}:
get:
summary: Get a deployment
tags:
- Deployments
security:
- AgentKey: []
parameters:
- name: deploymentId
in: path
required: true
schema:
type: string
pattern: ^inst_[0-9a-f]+$
example: inst_07d7eab4fabc
responses:
'200':
description: OK
content:
application/json:
schema:
type: object
properties:
success:
type: boolean
const: true
data:
type: object
properties:
deployment:
$ref: '#/components/schemas/Deployment'
instance:
$ref: '#/components/schemas/Deployment'
deprecated: true
description: Deprecated alias of `deployment`; returned until 2027-04-02.
meta:
$ref: '#/components/schemas/Meta'
required:
- success
- data
- meta
'404':
$ref: '#/components/responses/NotFound'
operationId: getV1DeploymentsByDeploymentId
x-operation-id-source: derived
delete:
summary: Delete a deployment
description: Stops billing immediately. The endpoint and API key stop working permanently.
tags:
- Deployments
security:
- AgentKey: []
parameters:
- name: deploymentId
in: path
required: true
schema:
type: string
pattern: ^inst_[0-9a-f]+$
example: inst_07d7eab4fabc
responses:
'200':
description: 'OK — `status: deleted`.'
'404':
$ref: '#/components/responses/NotFound'
operationId: deleteV1DeploymentsByDeploymentId
x-operation-id-source: derived
patch:
summary: Update a deployment's label / webhook
tags:
- Deployments
security:
- AgentKey: []
parameters:
- name: deploymentId
in: path
required: true
schema:
type: string
pattern: ^inst_[0-9a-f]+$
example: inst_07d7eab4fabc
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
label:
type: string
maxLength: 120
webhook_url:
type: string
nullable: true
format: uri
responses:
'200':
description: OK
operationId: patchV1DeploymentsByDeploymentId
x-operation-id-source: derived
/v1/deployments/{deploymentId}/throughput:
post:
summary: Change a deployment's throughput
description: Sets Standard / Double / Quad / Max. Same model and answer quality; more simultaneous requests and a higher per-hour rate. The endpoint and API key are unchanged. Pay-as-you-go only.
tags:
- Deployments
security:
- AgentKey: []
parameters:
- name: deploymentId
in: path
required: true
schema:
type: string
pattern: ^inst_[0-9a-f]+$
example: inst_07d7eab4fabc
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- throughput
- confirm
properties:
throughput:
oneOf:
- enum:
- standard
- double
- quad
- max
- type: integer
enum:
- 1
- 2
- 4
- 8
description: Throughput level. More throughput handles more simultaneous requests at the same answer quality. Double, Quad, and Max cost 1.9×, 3.75×, and 7.5× the Standard rate. Numbers 1/2/4/8 are accepted as aliases.
capacity:
type: integer
enum:
- 1
- 2
- 4
- 8
deprecated: true
description: Deprecated alias of `throughput`; returned until 2027-04-02.
confirm:
type: boolean
const: true
description: Acknowledges the billing change.
example:
throughput: double
confirm: true
responses:
'200':
description: OK
'409':
$ref: '#/components/responses/Conflict'
operationId: postV1DeploymentsByDeploymentIdThroughput
x-operation-id-source: derived
/v1/deployments/{deploymentId}/switch-model:
post:
summary: Switch the model on a deployment
description: Same-plan switches only. Starts the new model and returns a `new_deployment_id` (about 3 minutes; the endpoint URL and api_key change).
tags:
- Deployments
security:
- AgentKey: []
parameters:
- name: deploymentId
in: path
required: true
schema:
type: string
pattern: ^inst_[0-9a-f]+$
example: inst_07d7eab4fabc
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- model
properties:
model:
type: string
example: qwen3.6-35b-a3b
responses:
'202':
description: Accepted — switch started.
'400':
description: Plan mismatch or invalid model.
'404':
$ref: '#/components/responses/NotFound'
'409':
$ref: '#/components/responses/Conflict'
operationId: postV1DeploymentsByDeploymentIdSwitchModel
x-operation-id-source: derived
/v1/deployments/{deploymentId}/knowledge-base:
get:
summary: List documents in a deployment's knowledge base
tags:
- Deployments
security:
- AgentKey: []
parameters:
- name: deploymentId
in: path
required: true
schema:
type: string
pattern: ^inst_[0-9a-f]+$
example: inst_07d7eab4fabc
responses:
'200':
description: OK
'404':
$ref: '#/components/responses/NotFound'
operationId: getV1DeploymentsByDeploymentIdKnowledgeBase
x-operation-id-source: derived
post:
summary: Add documents to a deployment's knowledge base
description: 'Either upload files (multipart/form-data, field `files`, up to 50 × 25 MB) — they''re added to your library and attached — or send JSON `{ document_ids: [...] }` to attach documents already in your library. Indexing runs in the background.'
tags:
- Deployments
security:
- AgentKey: []
parameters:
- name: deploymentId
in: path
required: true
schema:
type: string
pattern: ^inst_[0-9a-f]+$
example: inst_07d7eab4fabc
requestBody:
required: true
content:
multipart/form-data:
schema:
type: object
properties:
files:
type: array
items:
type: string
format: binary
application/json:
schema:
type: object
properties:
document_ids:
type: array
items:
type: string
format: uuid
responses:
'202':
description: Accepted
'400':
description: No files or document_ids.
operationId: postV1DeploymentsByDeploymentIdKnowledgeBase
x-operation-id-source: derived
/v1/deployments/{deploymentId}/diagnostics:
get:
summary: Diagnose a deployment
description: 'Last-24h request volume, error rate and latency, plus recommendations. Keeps two levers separate: increase throughput (more simultaneous requests, same quality) vs move to a more capable model (better answers).'
tags:
- Deployments
security:
- AgentKey: []
parameters:
- name: deploymentId
in: path
required: true
schema:
type: string
pattern: ^inst_[0-9a-f]+$
example: inst_07d7eab4fabc
responses:
'200':
description: OK
'404':
$ref: '#/components/responses/NotFound'
operationId: getV1DeploymentsByDeploymentIdDiagnostics
x-operation-id-source: derived
/v1/deployments/{deploymentId}/system-prompt:
post:
summary: Set or clear the per-deployment system prompt
description: When set, overrides the account-level default. Empty string or null clears the override.
tags:
- Deployments
security:
- AgentKey: []
parameters:
- name: deploymentId
in: path
required: true
schema:
type: string
pattern: ^inst_[0-9a-f]+$
example: inst_07d7eab4fabc
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
system_prompt:
type: string
nullable: true
maxLength: 5000
responses:
'200':
description: OK
operationId: postV1DeploymentsByDeploymentIdSystemPrompt
x-operation-id-source: derived
components:
schemas:
Error404:
type: object
properties:
success:
type: boolean
const: false
error:
type: object
properties:
code:
type: string
example: DEPLOYMENT_NOT_FOUND
message:
type: string
docs:
type: string
format: uri
legacy_code:
type: string
description: 'On /v1/deployments/* routes: the pre-2026 name of a renamed code (e.g. INSTANCE_NOT_FOUND). Present until 2027-04-02.'
renamed_to:
type: string
description: 'On deprecated routes: the new name of a renamed code (e.g. DEPLOYMENT_NOT_FOUND).'
required:
- code
- message
- docs
meta:
$ref: '#/components/schemas/Meta'
required:
- success
- error
- meta
Deployment:
type: object
properties:
deployment_id:
type: string
example: inst_07d7eab4fabc
instance_id:
type: string
deprecated: true
description: Deprecated alias of `deployment_id`; returned until 2027-04-02.
status:
enum:
- deploying
- ready
- paused
- warming
- switching
- suspended
- error
- deleted
description: On /v1/deployments/* routes. (Deprecated routes return the pre-2026 value here and the new one in `deployment_status`.)
legacy_status:
type: string
description: Pre-2026 status value (e.g. `running` for `ready`); returned until 2027-04-02.
model:
type: string
example: qwen3.5-9b
billing:
enum:
- subscription
- pay_as_you_go
- on_demand
description: Current billing mode. `pay_as_you_go` is canonical; `on_demand` is a back-compat alias; `subscription` is legacy and applies only to grandfathered accounts.
label:
type: string
nullable: true
endpoint:
type: string
nullable: true
example: https://api.auxen.ai/v1/inst_07d7eab4fabc
description: Inference endpoint. OpenAI-compatible base URL is `{endpoint}/v1`.
api_key:
type: string
nullable: true
example: auxk_…
description: Per-deployment inference key. Use this in Authorization for /chat and /v1/chat/completions.
webhook_url:
type: string
nullable: true
throughput:
enum:
- standard
- double
- quad
- max
throughput_multiplier:
type: integer
enum:
- 1
- 2
- 4
- 8
capacity:
type: integer
enum:
- 1
- 2
- 4
- 8
deprecated: true
description: Deprecated alias of `throughput_multiplier`; returned until 2027-04-02.
system_prompt:
type: string
nullable: true
description: Per-deployment system prompt. null = inherit account default.
billing_details:
oneOf:
- type: object
properties:
mode:
const: subscription
plan:
enum:
- shared
- dedicated
- business
- enterprise
monthly_cost:
type: number
next_billing_date:
type: string
nullable: true
- type: object
properties:
mode:
const: pay_as_you_go
rate_per_hour:
type: string
example: $0.20/hour
hourly_rate:
type: number
deprecated: true
description: Deprecated alias of `rate_per_hour`; returned until 2027-04-02.
accumulated_cost:
type: number
spending_cap:
type: number
nullable: true
paused_at:
type: string
nullable: true
format: date-time
created_at:
type: string
format: date-time
ready_at:
type: string
nullable: true
format: date-time
deleted_at:
type: string
nullable: true
format: date-time
destroyed_at:
type: string
nullable: true
format: date-time
deprecated: true
description: Deprecated alias of `deleted_at`; returned until 2027-04-02.
Error409:
type: object
properties:
success:
type: boolean
const: false
error:
type: object
properties:
code:
type: string
example: DEPLOYMENT_NOT_FOUND
message:
type: string
docs:
type: string
format: uri
legacy_code:
type: string
description: 'On /v1/deployments/* routes: the pre-2026 name of a renamed code (e.g. INSTANCE_NOT_FOUND). Present until 2027-04-02.'
renamed_to:
type: string
description: 'On deprecated routes: the new name of a renamed code (e.g. DEPLOYMENT_NOT_FOUND).'
required:
- code
- message
- docs
meta:
$ref: '#/components/schemas/Meta'
required:
- success
- error
- meta
Meta:
type: object
properties:
requestId:
type: string
example: req_abcdef0123456789
timestamp:
type: string
format: date-time
responses:
Conflict:
description: Conflict with current resource state.
content:
application/json:
schema:
$ref: '#/components/schemas/Error409'
NotFound:
description: Resource not found.
content:
application/json:
schema:
$ref: '#/components/schemas/Error404'
securitySchemes:
AgentKey:
type: http
scheme: bearer
bearerFormat: auxen_live_xxx | auxen_test_xxx
description: Account-level key. Generate at /dashboard/api-keys.
DeploymentKey:
type: http
scheme: bearer
bearerFormat: auxk_xxx
description: Per-deployment key from the `api_key` field of a deployment object.