> ## Documentation Index > Fetch the complete documentation index at: https://runcrate.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Rerun job > Runs the job's spec again as a new job (`rerun_of` set), with any field of `POST /jobs` in the body replacing the job's own, e.g. `{ "gpu_count": 2 }`. The env values the job was given are reused (they are kept encrypted with it for 30 days after it ends); `env` in the body is merged over them. Only whoever submitted the job reuses them: anyone else sends every `env` value again. `Idempotency-Key` works as on `POST /jobs`. ## OpenAPI ````yaml /api-reference/openapi.json post /jobs/{id}/rerun openapi: 3.1.0 info: title: Runcrate API version: 1.0.0 summary: OpenAI-compatible inference API + GPU infrastructure API. description: >- Runcrate exposes two API surfaces. The inference API at `https://api.runcrate.ai/v1` is OpenAI-compatible: it accepts the standard OpenAI SDK with the base URL changed. The infrastructure API at `https://www.runcrate.ai/api/v1` manages GPU instances, jobs, persistent volumes, environments, SSH keys, templates, and billing. Both share a single `rc_live_*` API key. Pricing is per-token, per-image, per-second, or per-minute on the inference API (varies by model; see https://www.runcrate.ai/api/models/catalog for live rates) and per-second on GPU rentals (see https://www.runcrate.ai/pricing for hourly rates per GPU class). All infrastructure API responses are wrapped in `{ "data": ... }`. List responses also include a `meta` object with pagination cursors. Error responses use `{ "error": { "code": "...", "message": "..." } }`. termsOfService: https://www.runcrate.ai/terms contact: name: Runcrate url: https://www.runcrate.ai/contact license: name: Proprietary url: https://www.runcrate.ai/terms servers: - url: https://api.runcrate.ai/v1 description: Inference API (OpenAI-compatible) - url: https://www.runcrate.ai/api/v1 description: >- Infrastructure API (instances, jobs, storage, environments, ssh-keys, templates, billing) security: - ApiKeyAuth: [] tags: - name: Chat description: OpenAI-compatible chat completions. - name: Images description: Text-to-image generation. - name: Videos description: Async text-to-video and image-to-video generation. - name: Audio description: Text-to-speech and speech-to-text. - name: Embeddings description: Vector embeddings for RAG and search. - name: Models description: Model catalog discovery. - name: Instances description: GPU instance lifecycle. - name: Jobs description: >- Run one command on its own GPU machine. The machine stops, and billing ends, when the command exits. - name: Schedules description: >- Start an instance or a job later: once at a set time, or on a repeating cron schedule in your timezone. - name: Storage description: Persistent volume management. - name: Environments description: Resource isolation containers within a workspace. - name: Secrets description: >- Names of the secrets an environment's machines get. Values are set in the dashboard and never returned. - name: SSH Keys description: SSH key management for instance access. - name: Templates description: Pre-built instance images and configurations. - name: Billing description: Credit balance, transactions, usage metrics. paths: /jobs/{id}/rerun: servers: - url: https://www.runcrate.ai/api/v1 post: tags: - Jobs summary: Rerun job description: >- Runs the job's spec again as a new job (`rerun_of` set), with any field of `POST /jobs` in the body replacing the job's own, e.g. `{ "gpu_count": 2 }`. The env values the job was given are reused (they are kept encrypted with it for 30 days after it ends); `env` in the body is merged over them. Only whoever submitted the job reuses them: anyone else sends every `env` value again. `Idempotency-Key` works as on `POST /jobs`. operationId: rerunJob parameters: - name: id in: path required: true schema: type: string - name: Idempotency-Key in: header required: false schema: type: string maxLength: 255 requestBody: required: false content: application/json: schema: type: object description: Any field of `JobCreateRequest`. responses: '200': description: >- A replay of an earlier rerun with the same `Idempotency-Key`. The `Idempotent-Replayed: true` header is set. headers: Idempotent-Replayed: description: '`true`: this answers an earlier request with the same key.' schema: type: string enum: - 'true' content: application/json: schema: type: object required: - data properties: data: oneOf: - $ref: '#/components/schemas/Job' - $ref: '#/components/schemas/JobGroupCreated' '201': description: The new job (or group, with `count` or `params`). content: application/json: schema: type: object required: - data properties: data: oneOf: - $ref: '#/components/schemas/Job' - $ref: '#/components/schemas/JobGroupCreated' '400': description: '`bad_request`: the volume cannot be used.' content: application/json: schema: $ref: '#/components/schemas/Error' '401': $ref: '#/components/responses/Unauthorized' '402': description: '`BUDGET_REACHED` or `insufficient_credits`, as on `POST /jobs`.' content: application/json: schema: $ref: '#/components/schemas/Error' '404': $ref: '#/components/responses/NotFound' '409': description: >- `conflict`: the volume is attached to another machine, or the `Idempotency-Key` was used with another request (`idempotency_conflict`) or is still being handled (`idempotency_in_progress`). content: application/json: schema: $ref: '#/components/schemas/Error' '422': $ref: '#/components/responses/ValidationError' '429': description: >- `rate_limited`: the workspace already has 500 jobs queued, starting or running across its environments. content: application/json: schema: $ref: '#/components/schemas/Error' '500': description: >- `internal_error`. When the job was created first, `details.job_id` names it and it is `failed`. content: application/json: schema: $ref: '#/components/schemas/Error' '502': description: '`launch_refused`: as on `POST /jobs`.' content: application/json: schema: $ref: '#/components/schemas/Error' '503': description: >- `service_unavailable`: as on `POST /jobs`. Retry after the `Retry-After` seconds. headers: Retry-After: description: Seconds to wait before trying again. schema: type: integer example: 60 content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: Job: type: object required: - id - name - status - command - gpu_type - gpu_count - max_runtime_minutes - env_keys - created_at description: >- One command run on its own fresh GPU machine. The machine stops, and billing ends, as soon as the command exits, hits `max_runtime_minutes` or is cancelled. properties: id: type: string format: uuid name: type: string description: Defaults to `job-`. status: type: string enum: - queued - starting - running - succeeded - failed - cancelled - timed_out description: >- `queued`: accepted and waiting for a machine (`queue_reason` says why when it waits: no capacity yet, the budget, or the group's `max_parallel`), also between the attempts of a retried job. `starting`: machine launching, setup running. `running`: command started (`started_at` set). Terminal states never change: `succeeded` (exit 0), `failed` (non-zero exit with `exit_code` set, or the machine failed or was stopped, or no capacity within `capacity_wait_minutes`, with `exit_code` null and `error` saying why), `cancelled` (cancelled through the API, CLI or MCP, or the machine was stopped from Instances), `timed_out` (an attempt hit `max_runtime_minutes`, counted from its `started_at`). command: type: string description: Run with bash in `/workspace`. gpu_type: type: string description: >- The GPU model the job runs (or last ran) on; the first of `gpu_candidates` until it has had a machine. gpu_count: type: integer minimum: 1 maximum: 8 gpu_candidates: type: array items: $ref: '#/components/schemas/GpuCandidate' description: The GPUs asked for, in the order they are tried. template: type: string nullable: true description: OS template the machine boots from. image: type: string nullable: true description: Container image the command runs in, if set. env_keys: type: array items: type: string description: >- Names of the environment variables passed in `env`. Values are stored only encrypted and never returned. storage_id: type: string nullable: true description: >- Volume mounted at `/workspace`. Files written there are saved back to it when the machine stops. max_runtime_minutes: type: integer minimum: 1 maximum: 10080 description: Per attempt. capacity_wait_minutes: type: integer minimum: 0 maximum: 1440 description: How long the job waits for capacity before it fails. queue_reason: type: string nullable: true enum: - no_capacity - budget - max_parallel - volume_busy description: Why a `queued` job waits. Null otherwise. next_attempt_at: type: string format: date-time nullable: true description: When a `queued` job is tried next. attempt: type: integer minimum: 1 description: The current attempt, 1-based. max_retries: type: integer minimum: 0 maximum: 10 retry_on: type: array items: type: string enum: - machine_failure - nonzero_exit retry_exit_codes: type: array items: type: integer attempts: type: array items: $ref: '#/components/schemas/JobAttempt' description: Every attempt, the current one last. tags: type: object additionalProperties: type: string group_id: type: string format: uuid nullable: true description: The group the job belongs to (`count` or `params`). job_index: type: integer minimum: 0 description: 0-based place in its group; 0 for a single job. rerun_of: type: string format: uuid nullable: true description: The job this one reran. webhook_url: type: string nullable: true description: The per-job callback, shown as its host and the end of its path. webhook_events: type: array items: type: string enum: - started - finished webhook_secret: type: string description: >- Only in the answer to the request that created the job, and only when the callback is signed with a secret of its own (the workspace had no webhook endpoint). Shown once. exit_code: type: integer nullable: true description: The command's exit code once it has exited. error: type: string nullable: true description: >- Why the job failed when the command did not exit on its own (e.g. budget reached, balance ran out, machine failed to start). instance_id: type: string nullable: true description: >- The machine running the current attempt. It also shows in `GET /instances` while it runs. environment_id: type: string created_at: type: string format: date-time started_at: type: string format: date-time nullable: true description: When the current attempt's command started. ended_at: type: string format: date-time nullable: true description: Set on every terminal status. cost_per_hour: type: number nullable: true description: USD per hour for the machine. cost_usd: type: number nullable: true description: >- Cost of every attempt's machine so far, from when each is running (setup included). Final once the job ends. Null before any machine runs. log_bytes: type: integer description: Bytes of output stored. logs_truncated: type: boolean description: True when output passed the 10 MB cap and the middle was dropped. code: type: - object - 'null' description: >- Where the code came from: `source` upload (`ref` the upload id, `sha256` once fetched) or git (`url`, `ref`, `commit` once fetched). properties: source: type: string enum: - upload - git url: type: string ref: type: - string - 'null' sha256: type: - string - 'null' commit: type: - string - 'null' allow_cpu_container: type: boolean image_registry_auth: type: - object - 'null' properties: username_env: type: string password_env: type: string artifacts_count: type: integer description: Outputs kept (see `/jobs/{id}/artifacts`). gpu_util_avg: type: - number - 'null' description: Average GPU utilization while the command ran, percent. gpu_mem_peak_mb: type: - integer - 'null' description: Peak GPU memory used by one GPU. JobGroupCreated: allOf: - $ref: '#/components/schemas/JobGroup' - type: object properties: jobs: type: array items: $ref: '#/components/schemas/Job' webhook_secret: type: string description: 'As on `Job`: shown once.' Error: type: object required: - error properties: error: type: object required: - code - message properties: code: type: string description: >- Machine-readable error code (e.g. `validation_error`, `unauthorized`, `not_found`, `insufficient_credits`, `rate_limited`, `internal_error`). message: type: string description: Human-readable error message. details: type: object additionalProperties: true description: Optional structured error context. GpuCandidate: type: object required: - gpu_type - gpu_count properties: gpu_type: type: string gpu_count: type: integer minimum: 1 maximum: 8 JobAttempt: type: object required: - attempt - status description: >- One run of the command on one machine. Every attempt but the last failed and was retried. properties: attempt: type: integer minimum: 1 deployment_id: type: string nullable: true description: The machine (an instance) the attempt ran on. status: type: string enum: - queued - starting - running - succeeded - failed - cancelled - timed_out exit_code: type: integer nullable: true error: type: string nullable: true started_at: type: string format: date-time nullable: true ended_at: type: string format: date-time nullable: true cost_usd: type: number nullable: true gpu_type: type: string gpu_count: type: integer region: type: string nullable: true JobGroup: type: object required: - id - count - max_parallel - status_counts - created_at description: >- The jobs started by one request with `count` or `params`. List them with `GET /jobs?group_id=`. properties: id: type: string format: uuid count: type: integer minimum: 1 maximum: 100 max_parallel: type: integer minimum: 1 maximum: 100 status_counts: type: object additionalProperties: type: integer description: >- How many of its jobs are in each status, e.g. `{ "running": 2, "queued": 6, "succeeded": 2, ... }`. cost_usd: type: number nullable: true description: All of its jobs, every attempt. created_at: type: string format: date-time responses: Unauthorized: description: Missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/Error' NotFound: description: Resource not found. content: application/json: schema: $ref: '#/components/schemas/Error' ValidationError: description: Request shape or values failed validation. content: application/json: schema: $ref: '#/components/schemas/Error' securitySchemes: ApiKeyAuth: type: http scheme: bearer description: >- Use a Runcrate API key with the `rc_live_*` prefix as the bearer token. Create one at https://www.runcrate.ai/dashboard/api-keys. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.