# Get model migration path

Returns the chain of models from the given model to the final active successor. Catalog-only, no scope needed.

RBAC:
- requires ANY of AIModels.Read, GroupAIModels.Read

Endpoint: GET /api/v1/ai-models/{modelId}/migration-path
Version: 1.0
Security: header

## Path parameters:

  - `modelId` (string, required)
    UUID with type prefix
    Example: "us_01hxcvk1hjexere4pvtrj0ymqq"

## Response 200 fields (application/json):

  - `modelId` (object, required)
    Model unique identifier

  - `providerId` (object, required)
    Provider this model belongs to

  - `externalId` (string, required)
    External model ID used by the provider (e.g., 'gpt-4.1')

  - `name` (string, required)
    Display name for the model

  - `enabled` (boolean,null, required)
    Whether the model is enabled in the requested scope (null if no scoped record)

  - `deprecated` (boolean, required)
    Whether the model is deprecated

  - `successorModelId` (string,null, required)
    Successor model ID if deprecated
    Example: "us_01hxcvk1hjexere4pvtrj0ymqq"

  - `capabilities` (object, required)
    Model capabilities

  - `capabilities.supportsChat` (boolean)
    Supports chat completions

  - `capabilities.supportsEmbeddings` (boolean)
    Supports embeddings generation

  - `capabilities.supportsTools` (boolean)
    Supports tool/function calling

  - `capabilities.supportsJsonSchema` (boolean)
    Supports JSON schema response format

  - `capabilities.supportsVision` (boolean)
    Supports image input (vision)

  - `capabilities.supportsStreaming` (boolean)
    Supports streaming responses

  - `capabilities.supportsReasoning` (boolean)
    Supports reasoning/chain-of-thought

  - `capabilities.supportsAttachments` (boolean)
    Supports file attachments (images, PDFs, etc.)

  - `capabilities.supportsTemperature` (boolean)
    Supports temperature parameter

  - `modalities` (array, required)
    Supported input/output modalities
    Enum: "TEXT", "IMAGE", "AUDIO", "VIDEO", "PDF"

  - `builtInTools` (array, required)
    Built-in tools supported natively by the provider for this model
    Enum: "WEB_SEARCH", "CODE_EXECUTION", "FILE_SEARCH", "COMPUTER_USE", "IMAGE_GENERATION", "TEXT_EDITOR", "BASH", "URL_CONTEXT", "MCP"

  - `limits` (object, required)
    Token limits

  - `limits.maxInputTokens` (integer,null)
    Maximum input tokens

  - `limits.maxOutputTokens` (integer,null)
    Maximum output tokens

  - `limits.contextWindow` (integer,null)
    Total context window size

  - `pricing` (object,null, required)
    Pricing information

  - `pricing.inputPer1MTokens` (number,null)
    Cost per 1M input tokens in USD

  - `pricing.outputPer1MTokens` (number,null)
    Cost per 1M output tokens in USD

  - `pricing.cacheReadPer1MTokens` (number,null)
    Cost per 1M cached read tokens in USD

  - `pricing.cacheWritePer1MTokens` (number,null)
    Cost per 1M cached write tokens in USD

  - `family` (string,null, required)
    Model family (e.g., 'gpt-4o', 'claude-opus')

  - `releaseDate` (string,null, required)
    Model release date

  - `knowledgeCutoff` (string,null, required)
    Knowledge cutoff date

  - `openWeights` (boolean, required)
    Whether model has open weights

  - `createdAt` (string, required)
    When the model was created
    Example: "2022-03-10T16:15:50Z"

  - `updatedAt` (string, required)
    When the model was last updated
    Example: "2022-03-10T16:15:50Z"