DeepInfra LoRA Adapters API

openapi: 3.2.0
info:
  title: DeepInfra LoRA Adapters API
  description: The DeepInfra API provides serverless AI inference, custom model deployments, and GPU rentals.
  version: 1.0.0
servers:
- url: https://api.deepinfra.com
tags:
- name: LoRA Adapters
  description: Create, manage, and query LoRA adapter models.
paths:
  /lora-model:
    post:
      tags:
      - LoRA Adapters
      summary: Upload Lora Model
      operationId: upload_lora_model_lora_model_post
      security:
      - HTTPBearer: []
      parameters:
      - name: xi-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Xi-Api-Key
      - name: x-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: X-Api-Key
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/LoraModelUploadIn'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeploymentOut'
        '400':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeepError'
          description: Bad Request
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /lora-model/{lora_model_name}:
    delete:
      tags:
      - LoRA Adapters
      summary: Delete Lora Model
      operationId: delete_lora_model_lora_model__lora_model_name__delete
      security:
      - HTTPBearer: []
      parameters:
      - name: lora_model_name
        in: path
        required: true
        schema:
          type: string
          title: Lora Model Name
      - name: xi-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Xi-Api-Key
      - name: x-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: X-Api-Key
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '400':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeepError'
          description: Bad Request
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/lora/create:
    post:
      tags:
      - LoRA Adapters
      summary: Create Lora
      operationId: create_lora_v1_lora_create_post
      security:
      - HTTPBearer: []
      parameters:
      - name: xi-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Xi-Api-Key
      - name: x-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: X-Api-Key
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateLoraApiRequest'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeploymentOut'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/lora/{lora_name}/status:
    get:
      tags:
      - LoRA Adapters
      summary: Get Lora Status
      operationId: get_lora_status_v1_lora__lora_name__status_get
      security:
      - HTTPBearer: []
      parameters:
      - name: lora_name
        in: path
        required: true
        schema:
          type: string
          title: Lora Name
      - name: xi-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Xi-Api-Key
      - name: x-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: X-Api-Key
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/lora/{lora_name}:
    get:
      tags:
      - LoRA Adapters
      summary: Get Lora
      operationId: get_lora_v1_lora__lora_name__get
      security:
      - HTTPBearer: []
      parameters:
      - name: lora_name
        in: path
        required: true
        schema:
          type: string
          title: Lora Name
      - name: xi-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Xi-Api-Key
      - name: x-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: X-Api-Key
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    patch:
      tags:
      - LoRA Adapters
      summary: Update Lora
      operationId: update_lora_v1_lora__lora_name__patch
      security:
      - HTTPBearer: []
      parameters:
      - name: lora_name
        in: path
        required: true
        schema:
          type: string
          title: Lora Name
      - name: xi-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Xi-Api-Key
      - name: x-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: X-Api-Key
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/UpdateLoraApiRequest'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    delete:
      tags:
      - LoRA Adapters
      summary: Delete Lora
      operationId: delete_lora_v1_lora__lora_name__delete
      security:
      - HTTPBearer: []
      parameters:
      - name: lora_name
        in: path
        required: true
        schema:
          type: string
          title: Lora Name
      - name: xi-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Xi-Api-Key
      - name: x-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: X-Api-Key
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/model/{model_name}/loras:
    get:
      tags:
      - LoRA Adapters
      summary: Get Model Loras
      operationId: get_model_loras_v1_model__model_name__loras_get
      security:
      - HTTPBearer: []
      parameters:
      - name: model_name
        in: path
        required: true
        schema:
          type: string
          title: Model Name
      - name: xi-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Xi-Api-Key
      - name: x-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: X-Api-Key
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/user/loras:
    get:
      tags:
      - LoRA Adapters
      summary: Get User Loras
      operationId: get_user_loras_v1_user_loras_get
      security:
      - HTTPBearer: []
      parameters:
      - name: xi-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Xi-Api-Key
      - name: x-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: X-Api-Key
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  schemas:
    DeployGPUs:
      type: string
      enum:
      - L4-24GB
      - L40S-48GB
      - A100-80GB
      - H100-80GB
      - H200-141GB
      - B200-180GB
      - B300-270GB
      - RTXPRO6000-96GB
      - other
      title: DeployGPUs
    DeployRollout:
      properties:
        up_to_date:
          type: integer
          title: Up To Date
          description: Instances serving the current config.
        outdated:
          type: integer
          title: Outdated
          description: Instances still serving a previous config.
        booting:
          type: integer
          title: Booting
          description: Instances starting up.
      type: object
      required:
      - up_to_date
      - outdated
      - booting
      title: DeployRollout
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    SourceModel:
      properties:
        type:
          $ref: '#/components/schemas/SourceTypeEnum'
        civit_url:
          anyOf:
          - type: string
          - type: 'null'
          title: Civit Url
      type: object
      required:
      - type
      title: SourceModel
    DeploymentOut:
      properties:
        type:
          $ref: '#/components/schemas/DeployType'
          default: legacy
        deploy_id:
          type: string
          title: Deploy Id
          description: Deploy Id
          examples:
          - fkj843kjh8
        model_name:
          type: string
          title: Model Name
          description: Model Id from huggingface
          examples:
          - google/vit-base-patch16-224
        version:
          type: string
          title: Version
          description: Model version
          examples:
          - d8b79b422843bd59d628bf25b01aded94a9ec1a9b917e69fe460df9ff39ec42b
        task:
          type: string
          title: Task
          description: Task
          examples:
          - image-classification
        status:
          type: string
          title: Status
          description: Status
          examples:
          - deployed
        fail_reason:
          type: string
          title: Fail Reason
          description: Failure reason
          examples:
          - Initialization failed
        created_at:
          type: string
          title: Created At
          description: Created at
          examples:
          - '2021-08-27T17:19:21+00:00'
        updated_at:
          type: string
          title: Updated At
          description: Updated at
          examples:
          - '2021-08-27T17:19:21+00:00'
        instances:
          anyOf:
          - $ref: '#/components/schemas/DeployInstances'
          - type: 'null'
          description: Details about number of instances running right now
        config:
          anyOf:
          - $ref: '#/components/schemas/DeployLLMConfig'
          - type: 'null'
          description: Immutable deploy configuration
        settings:
          anyOf:
          - $ref: '#/components/schemas/ScaleSettings'
          - type: 'null'
          description: Scale Settings
        standard_args:
          properties:
            max_context_size:
              anyOf:
              - type: integer
                maximum: 10000000.0
                minimum: 1.0
              - type: 'null'
              title: Max Context Size
              description: Maximum total sequence length (prompt + generation).
            max_concurrent_requests:
              anyOf:
              - type: integer
                maximum: 1024.0
                minimum: 1.0
              - type: 'null'
              title: Max Concurrent Requests
              description: Max number of requests served concurrently.
            max_images_per_prompt:
              anyOf:
              - type: integer
                maximum: 1024.0
                minimum: 0.0
              - type: 'null'
              title: Max Images Per Prompt
              description: Images the engine accepts in one request; deepapi refuses more before rendering. 0 disables image input entirely.
            gpu_memory_fraction:
              anyOf:
              - type: number
                maximum: 0.97
                minimum: 0.5
              - type: 'null'
              title: Gpu Memory Fraction
              description: Fraction of GPU memory the engine may use for weights + KV cache.
            max_prefill_tokens:
              anyOf:
              - type: integer
                maximum: 131072.0
                minimum: 512.0
              - type: 'null'
              title: Max Prefill Tokens
              description: Max tokens processed per prefill/engine step (chunked prefill size).
            kv_cache_dtype:
              anyOf:
              - type: string
                enum:
                - auto
                - fp8
              - type: 'null'
              title: Kv Cache Dtype
              description: KV cache precision. fp8 ~doubles KV capacity at <1% accuracy loss.
            enable_prefix_caching:
              anyOf:
              - type: boolean
              - type: 'null'
              title: Enable Prefix Caching
              description: Reuse KV cache for shared prompt prefixes.
            quantization:
              anyOf:
              - type: string
                enum:
                - fp8
                - awq
                - gptq
                - awq_marlin
                - gptq_marlin
                - compressed-tensors
                - bitsandbytes
              - type: 'null'
              title: Quantization
              description: On-the-fly weight quantization method.
          additionalProperties: false
          type: object
          title: StandardArgs
          description: Current engine tuning knobs
        extra_args:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Extra Args
          description: Current extra engine-specific command-line args (custom-weight deploys only)
        update_error:
          anyOf:
          - type: string
          - type: 'null'
          title: Update Error
          description: If the last config update was auto-reverted after an engine crash-loop, the error that caused it (status stays 'running')
        rollout:
          anyOf:
          - $ref: '#/components/schemas/DeployRollout'
          - type: 'null'
          description: Per-instance rollout progress of the current config
      type: object
      required:
      - deploy_id
      - model_name
      - version
      - task
      - status
      - fail_reason
      - created_at
      - updated_at
      title: DeploymentOut
    SourceTypeEnum:
      type: string
      enum:
      - civitai
      title: SourceTypeEnum
    UpdateLoraApiRequest:
      properties:
        private:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Private
        description:
          anyOf:
          - type: string
          - type: 'null'
          title: Description
      type: object
      title: UpdateLoraApiRequest
    CreateLoraApiRequest:
      properties:
        base_model:
          type: string
          title: Base Model
        lora_name:
          type: string
          title: Lora Name
        source:
          $ref: '#/components/schemas/SourceModel'
        private:
          type: boolean
          title: Private
        description:
          anyOf:
          - type: string
          - type: 'null'
          title: Description
          default: ''
      type: object
      required:
      - base_model
      - lora_name
      - source
      - private
      title: CreateLoraApiRequest
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    DeepError:
      properties:
        error:
          type: string
          title: Error
          description: Error
          examples:
          - Model not found
      type: object
      required:
      - error
      title: DeepError
    DeployType:
      type: string
      enum:
      - legacy
      - llm
      - lora
      - tts
      title: DeployType
    ScaleSettings:
      properties:
        min_instances:
          type: integer
          title: Min Instances
          description: Minimum number of model instances to run
          default: 1
        max_instances:
          type: integer
          title: Max Instances
          description: Maximum number of model instances to run
          default: 1
      type: object
      title: ScaleSettings
    LoraModelUploadIn:
      properties:
        hf_model_name:
          type: string
          title: Hf Model Name
        hf_token:
          anyOf:
          - type: string
          - type: 'null'
          title: Hf Token
        lora_model_name:
          type: string
          title: Lora Model Name
        base_model_name:
          anyOf:
          - type: string
          - type: 'null'
          title: Base Model Name
      type: object
      required:
      - hf_model_name
      - lora_model_name
      title: LoraModelUploadIn
    DeployLLMConfig:
      properties:
        gpu:
          $ref: '#/components/schemas/DeployGPUs'
          description: The type of GPU the deployment is running on
        num_gpus:
          type: integer
          title: Num Gpus
          description: Number of GPUs used by one instance
        max_batch_size:
          type: integer
          title: Max Batch Size
          description: Maximum number of concurrent requests
        weights:
          anyOf:
          - $ref: '#/components/schemas/HFWeights'
          - type: 'null'
          description: Model weights information
      type: object
      required:
      - gpu
      - num_gpus
      - max_batch_size
      title: DeployLLMConfig
    HFWeights:
      properties:
        repo:
          type: string
          title: Repo
          description: huggingface repository i.e username/reponame
        revision:
          anyOf:
          - type: string
          - type: 'null'
          title: Revision
          description: commit sha or branch name
        token:
          anyOf:
          - type: string
          - type: 'null'
          title: Token
          description: huggingface access token with read access to the repo
      type: object
      required:
      - repo
      title: HFWeights
    DeployInstances:
      properties:
        running:
          type: integer
          title: Running
          description: Instances serving at full capacity.
        pending:
          type: integer
          title: Pending
          description: Instances still starting up.
        warming:
          type: integer
          title: Warming
          description: Instances that are up but still warming up, so they take a reduced share of the traffic.
          default: 0
      type: object
      required:
      - running
      - pending
      title: DeployInstances
      description: 'A deployment''s capacity: running + pending + warming.'
  securitySchemes:
    HTTPBearer:
      type: http
      scheme: bearer