Create batch inference job (Bedrock format)

Creates a batch inference job using AWS Bedrock format. Routes to native Bedrock by default; set x-model-provider to route the job to another provider (openai, gemini, etc.).

POST /bedrock/model-invocation-job

Error

A valid request URL is required to generate request examples

200

{
  "jobArn": "<string>",
  "jobName": "<string>",
  "modelId": "<string>",
  "roleArn": "<string>",
  "inputDataConfig": {},
  "outputDataConfig": {},
  "vpcConfig": {
    "securityGroupIds": [
      "<string>"
    ],
    "subnetIds": [
      "<string>"
    ]
  },
  "submitTime": "2023-11-07T05:31:56Z",
  "lastModifiedTime": "2023-11-07T05:31:56Z",
  "endTime": "2023-11-07T05:31:56Z",
  "message": "<string>",
  "clientRequestToken": "<string>",
  "jobExpirationTime": "2023-11-07T05:31:56Z",
  "timeoutDurationInHours": 123
}

Authorizations

BearerAuthBasicAuthVirtualKeyAuthApiKeyAuth

Authorization · string · header · required

Bearer token authentication. Use your provider API key or Bifrost authentication token. Virtual keys (prefixed with sk-bf-) can also be passed here.

Headers

x-model-provider · string

Optional provider override for cross-provider batch routing.

Body

application/json

roleArn · string · required

IAM role ARN for the job

inputDataConfig · object · required

Show child attributes

outputDataConfig · object · required

Show child attributes

modelId · string

Model ID for the batch job (optional, can be specified in request)

jobName · string

Name for the batch job

timeoutDurationInHours · integer

Timeout in hours

tags · object[]

Show child attributes

Response

200

application/json

Successful response

jobArn · string

status · enum<string>

Available options: Submitted, InProgress, Completed, Failed, Stopping, Stopped, PartiallyCompleted, Expired, Validating, Scheduled

jobName · string

modelId · string

roleArn · string

inputDataConfig · object

outputDataConfig · object

vpcConfig · object

Show child attributes

submitTime · string<date-time>

lastModifiedTime · string<date-time>

endTime · string<date-time>

message · string

clientRequestToken · string

jobExpirationTime · string<date-time>

timeoutDurationInHours · integer