llms.txtllms-full.txt
DashboardStatusGet API Key
IntroductionQuickstartModelsPricingArchitecture & SecurityLimits & Quotas
Execution Modes & HTTP QueueWebhooksWebSocketsMCP Servern8n Integrationn8n dryAPI node
API OverviewErrorsText-to-ImagePOSTText-to-Image Price CalculationPOSTText-to-VideoPOSTText-to-Video Price CalculationPOSTImage-to-VideoPOSTImage-to-Video Price CalculationPOSTAudio-to-VideoPOSTAudio-to-Video Price CalculationPOSTText-to-Speech (TTS)POSTText-to-Speech Price CalculationPOSTText-to-MusicPOSTText-to-Music Price CalculationPOSTText-to-EmbeddingPOSTText-to-Embedding Price CalculationPOSTImage-to-ImagePOSTImage-to-Image Price CalculationPOSTImage Background RemovalPOSTImage Background Removal Price CalculationPOSTImage UpscalePOSTImage Upscale Price CalculationPOST
OpenAPI
OpenAPI ReferenceJobsOpenAI CompatibleRunPod JobsWebhooks POST
SDKs & IntegrationsPayment MethodsFAQ — Frequently Asked QuestionsSupport & Contact
dAdryAPI
DashboardStatusGet API Key
APIAPI Reference
Technical Reference

RunPod Jobs

Direct provider operational routes for run, runsync, status, and queue control.

Submit asynchronous RunPod job

POST
/v1/runpod/{surface}/run

Authorization

BearerAuth
AuthorizationBearer <token>

Use Authorization: Bearer <api-key>.

In: header

Path Parameters

surface*|||

Inference surface used to select the provider endpoint.

Query Parameters

endpointId?string

Optional provider endpoint override. If omitted, routing uses surface/model mapping.

Length1 <= length

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

Response Body

application/json

curl -X POST "https://loading/v1/runpod/chat/run" \  -H "Content-Type: application/json" \  -d '{}'
{
  "id": "f3de27f8-61d5-4d58-aad1-a7d63f8a6e0f",
  "status": "IN_QUEUE"
}
Empty
Empty
Empty
Empty
Empty

Submit synchronous RunPod job

POST
/v1/runpod/{surface}/runsync

Authorization

BearerAuth
AuthorizationBearer <token>

Use Authorization: Bearer <api-key>.

In: header

Path Parameters

surface*|||

Inference surface used to select the provider endpoint.

Query Parameters

endpointId?string

Optional provider endpoint override. If omitted, routing uses surface/model mapping.

Length1 <= length

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

Response Body

application/json

curl -X POST "https://loading/v1/runpod/chat/runsync" \  -H "Content-Type: application/json" \  -d '{}'
{
  "id": "f3de27f8-61d5-4d58-aad1-a7d63f8a6e0f",
  "status": "COMPLETED",
  "output": {
    "data": [
      {
        "embedding": [
          0.132,
          -0.018,
          0.004
        ]
      }
    ]
  }
}
Empty
Empty
Empty
Empty
Empty

Get RunPod job status

GET
/v1/runpod/{surface}/status/{jobId}

Authorization

BearerAuth
AuthorizationBearer <token>

Use Authorization: Bearer <api-key>.

In: header

Path Parameters

surface*|||

Inference surface used to select the provider endpoint.

jobId*string

Provider job identifier returned when a request is accepted.

Length1 <= length

Query Parameters

endpointId?string

Optional provider endpoint override. If omitted, routing uses surface/model mapping.

Length1 <= length

Response Body

curl -X GET "https://loading/v1/runpod/images/status/f3de27f8-61d5-4d58-aad1-a7d63f8a6e0f"
Empty
Empty
Empty
Empty
Empty
Empty
Empty

Stream RunPod job output

GET
/v1/runpod/{surface}/stream/{jobId}

Authorization

BearerAuth
AuthorizationBearer <token>

Use Authorization: Bearer <api-key>.

In: header

Path Parameters

surface*|||

Inference surface used to select the provider endpoint.

jobId*string

Provider job identifier returned when a request is accepted.

Length1 <= length

Query Parameters

endpointId?string

Optional provider endpoint override. If omitted, routing uses surface/model mapping.

Length1 <= length

Response Body

curl -X GET "https://loading/v1/runpod/images/stream/f3de27f8-61d5-4d58-aad1-a7d63f8a6e0f"
Empty
Empty
Empty
Empty
Empty
Empty

Cancel RunPod job

POST
/v1/runpod/{surface}/cancel/{jobId}

Authorization

BearerAuth
AuthorizationBearer <token>

Use Authorization: Bearer <api-key>.

In: header

Path Parameters

surface*|||

Inference surface used to select the provider endpoint.

jobId*string

Provider job identifier returned when a request is accepted.

Length1 <= length

Query Parameters

endpointId?string

Optional provider endpoint override. If omitted, routing uses surface/model mapping.

Length1 <= length

Response Body

curl -X POST "https://loading/v1/runpod/images/cancel/f3de27f8-61d5-4d58-aad1-a7d63f8a6e0f"
Empty
Empty
Empty
Empty
Empty
Empty
Empty

Retry RunPod job

POST
/v1/runpod/{surface}/retry/{jobId}

Authorization

BearerAuth
AuthorizationBearer <token>

Use Authorization: Bearer <api-key>.

In: header

Path Parameters

surface*|||

Inference surface used to select the provider endpoint.

jobId*string

Provider job identifier returned when a request is accepted.

Length1 <= length

Query Parameters

endpointId?string

Optional provider endpoint override. If omitted, routing uses surface/model mapping.

Length1 <= length

Response Body

curl -X POST "https://loading/v1/runpod/images/retry/f3de27f8-61d5-4d58-aad1-a7d63f8a6e0f"
Empty
Empty
Empty
Empty
Empty
Empty
Empty

Purge RunPod pending queue

POST
/v1/runpod/{surface}/purge-queue

Authorization

BearerAuth
AuthorizationBearer <token>

Use Authorization: Bearer <api-key>.

In: header

Path Parameters

surface*|||

Inference surface used to select the provider endpoint.

Query Parameters

endpointId?string

Optional provider endpoint override. If omitted, routing uses surface/model mapping.

Length1 <= length

Response Body

curl -X POST "https://loading/v1/runpod/chat/purge-queue"
Empty
Empty
Empty
Empty
Empty
Empty

Get RunPod endpoint health

GET
/v1/runpod/{surface}/health

Authorization

BearerAuth
AuthorizationBearer <token>

Use Authorization: Bearer <api-key>.

In: header

Path Parameters

surface*|||

Inference surface used to select the provider endpoint.

Query Parameters

endpointId?string

Optional provider endpoint override. If omitted, routing uses surface/model mapping.

Length1 <= length

Response Body

curl -X GET "https://loading/v1/runpod/chat/health"
Empty
Empty
Empty
Empty
Empty
Empty
Last updated on 21 March 2026

OpenAI Compatible

OpenAI/OpenRouter-style inference enqueue endpoints.

Webhooks POST

Webhook signature and delivery testing routes.

endpointId?string

Explicit RunPod endpoint ID. Overrides default endpoint mapping when provided.

Length1 <= length
model?string

Model slug used for endpoint routing and cost estimation.

Value in"AceStep_1_5_Turbo" | "Ben2" | "Bge_M3_INT8" | "Flux_2_Klein_4B_BF16" | "Ltx2_3_22B_Dist_INT8" | "Nanonets_Ocr_S_F16" | "Qwen3_TTS_12Hz_1_7B_CustomVoice" | "RealESRGAN_x4" | "WhisperLargeV3" | "ZImageTurbo_INT8"
worker_type?|

Optional worker type hint for dynamic pricing (active or flex).

input?

Provider input payload forwarded to RunPod as input.

webhook?string

Deprecated webhook alias. Prefer webhook_url.

Formaturi
webhook_url?string

HTTPS URL that receives signed status updates for this job.

Formaturi
policy?

Optional policy hints used by gateway routing and execution controls.

s3Config?

Optional object-storage output configuration for provider artifacts.

[key: string]?any
endpointId?string

Explicit RunPod endpoint ID. Overrides default endpoint mapping when provided.

Length1 <= length
model?string

Model slug used for endpoint routing and cost estimation.

Value in"AceStep_1_5_Turbo" | "Ben2" | "Bge_M3_INT8" | "Flux_2_Klein_4B_BF16" | "Ltx2_3_22B_Dist_INT8" | "Nanonets_Ocr_S_F16" | "Qwen3_TTS_12Hz_1_7B_CustomVoice" | "RealESRGAN_x4" | "WhisperLargeV3" | "ZImageTurbo_INT8"
worker_type?|

Optional worker type hint for dynamic pricing (active or flex).

input?

Provider input payload forwarded to RunPod as input.

webhook?string

Deprecated webhook alias. Prefer webhook_url.

Formaturi
webhook_url?string

HTTPS URL that receives signed status updates for this job.

Formaturi
policy?

Optional policy hints used by gateway routing and execution controls.

s3Config?

Optional object-storage output configuration for provider artifacts.

[key: string]?any