> ## Documentation Index > Fetch the complete documentation index at: https://vastai-80aa3a82-auto-openapi-update-79df5d46.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Create or Update Deployment > Creates a new deployment or updates an existing one by name/tag, returning an S3 upload URL when a new file version needs to be uploaded. ## OpenAPI ````yaml /api-reference/openapi.yaml put /api/v0/deployments/ openapi: 3.1.0 info: title: Vast.ai API description: >- Vast.ai REST API for managing GPU cloud instances, machine operations, and AI/ML workflows. ## AI Agent Quick-Start Install the CLI skill for your agent (Claude Code, Cursor, Windsurf, etc.): npx skills add vast-ai/vast-cli CLI reference: https://raw.githubusercontent.com/vast-ai/vast-cli/master/vastai/SKILL.md SDK reference: https://raw.githubusercontent.com/vast-ai/vast-cli/master/vastai_sdk/SKILL.md ## Auth All endpoints require `Authorization: Bearer $VAST_API_KEY`. Get your key at: https://cloud.vast.ai/manage-keys/ ## Key Quirks - `gpu_ram` in CLI = GB; in REST API = MB (CLI auto-converts) - SSH keys must be registered BEFORE creating an instance (VM: no recovery; Docker: can add post-create) - `onstart` field is limited to 4048 characters -- gzip+base64 for longer scripts - `POST /api/v0/asks/{id}/` (create instance) returns `new_contract` as the instance ID, not `id` - Poll trap: if `actual_status` becomes `exited`, `unknown`, or `offline` it will never reach `running` -- destroy and retry version: 1.0.0 contact: name: Vast.ai Support url: https://discord.gg/vast servers: - url: https://console.vast.ai description: Production server security: - BearerAuth: [] paths: /api/v0/deployments/: put: tags: - Serverless summary: Create or Update Deployment description: >- Creates a new deployment or updates an existing one by name/tag, returning an S3 upload URL when a new file version needs to be uploaded. requestBody: content: application/json: schema: type: object properties: name: type: string description: >- Deployment name (letters, numbers, hyphens, dots, underscores; must start with letter or number; max 128 chars). example: my-model tag: type: string description: >- Deployment tag used to differentiate variants of the same named deployment; defaults to 'default'. example: v2 image: type: string description: Docker image to run on worker instances; required. example: pytorch/pytorch:2.0.0 search_params: type: string description: GPU offer filter expression for selecting worker machines. example: gpu_ram>=16 num_gpus=1 file_hash: type: string description: >- SHA-256 (or similar) hash of the deployment artifact to upload; required and used as a cache key. example: e3b0c44298fc1c149afb file_size: type: integer description: >- Size in bytes of the deployment artifact; required when file_hash is provided. example: 1048576 env: type: string description: >- Environment variable string to inject into workers (e.g. '-e FOO=bar'). example: '-e MODEL=llama' storage: type: number description: >- Disk storage to allocate per worker in GB; must be positive; defaults to 50. example: 100 ttl: type: number description: >- Seconds after the last heartbeat before the deployment is automatically deleted; negative disables auto-expiry. example: 3600 version_label: type: string description: >- Human-readable label for this artifact version; defaults to first 6 chars of file_hash. example: release-1.0 docker_login_user: type: string description: Docker registry username for pulling private images. docker_login_pass: type: string description: Docker registry password for pulling private images. docker_login_repo: type: string description: Docker registry hostname/repo to authenticate against. example: docker.io cold_workers: type: integer description: >- Fixed number of cold standby workers for the backing endpoint. example: 2 max_workers: type: integer description: Maximum number of workers for the backing endpoint. example: 10 min_load: type: number description: Minimum load threshold for the backing endpoint. example: 0 min_cold_load: type: number description: Minimum cold load threshold for the backing endpoint. example: 0 target_util: type: number description: Target utilization ratio (0-1) for the backing endpoint. example: 0.9 cold_mult: type: number description: Cold-standby multiplier for the backing endpoint. example: 3 max_queue_time: type: number description: Maximum acceptable queue time in seconds. example: 60 target_queue_time: type: number description: Target queue time in seconds. example: 10 inactivity_timeout: type: number description: Seconds of inactivity before the endpoint may be suspended. example: 300 overrecruit_ratio: type: number description: >- Ratio by which to over-recruit workers for traffic spike absorption. example: 1.2 autoscaler_instance: type: string description: Autoscaler deployment environment. example: prod responses: '200': description: >- Returns {success: true, action: 'created'|'soft_update'|'autoscale_update'|'exists', deployment_id, endpoint_id, upload_url?, upload_fields?, evicted_versions?} content: application/json: schema: type: object properties: success: type: boolean description: Always true on success. action: type: string description: 'One of: created, soft_update, autoscale_update, exists.' deployment_id: type: integer description: ID of the deployment. endpoint_id: type: integer description: ID of the associated endpoint. upload_url: type: string description: >- Presigned S3 URL to upload the deployment blob (present when a new version needs to be uploaded). upload_fields: type: object description: >- Additional fields required for the S3 multipart POST upload (present with upload_url). evicted_versions: type: array description: >- List of evicted version objects ({id, file_hash, version_label, file_size}) if LRU eviction occurred. items: type: object example: success: true action: created deployment_id: 5 endpoint_id: 10 upload_url: https://s3.amazonaws.com/bucket/... upload_fields: key: 1/myapp/abc123 AWSAccessKeyId: ... '400': description: >- Invalid or missing required params: name, tag, image, file_hash, file_size, storage; or storage limit exceeded content: application/json: schema: $ref: '#/components/schemas/Error' '403': description: Host-only accounts cannot create deployments or use serverless content: application/json: schema: $ref: '#/components/schemas/Error' security: - BearerAuth: [] components: schemas: Error: type: object properties: error: type: string msg: type: string securitySchemes: BearerAuth: type: http scheme: bearer description: API key must be provided in the Authorization header ````