---
title: "Get Model"
method: GET
path: "/v4/organizations/{organizationId}/aiServices/models/{modelId}"
tags: ["Models (AI Data Plane)"]
---

# Get Model

`GET /v4/organizations/{organizationId}/aiServices/models/{modelId}`

Fetches the details of the given model.

In order to access this endpoint, the provided API key must have at least one of the following roles:
- Organization Member

To learn more, see [Organization, Project, and Database Access Overview](https://docs.couchbase.com/cloud/organizations/organization-projects-overview.html).

## Response `200`

Successfully fetched the model based on the ModelId.

- GetLanguageModelResponse — Response schema for getting a language model
  - `model` object
    - `id` string, uuid — Unique identifier for the language model.
    - `name` string — Name of the deployed model.
    - `config` Config — Contains all the model information.
      - `catalogModelName` string — Name of the model deployed from the model catalog.
      - `type` 'text-generation' | 'embedding-generation' | 'moderation' | 'prompt-injection' — The kind of model.
      - `provider` 'meta' | 'nvidia' — The provider of the model.
      - `quantization` 'fp8' | 'fp16' | 'fullPrecision' — Quantization options for the model. Options include 8-bit, 16bit, and full-precision.
      - `optimization` 'throughput' | 'latency' — Optimization profile option for the model.
      - `dimensions` integer — Dimensions specifies the number of dimensions for the embedding vectors. This field is only present and relevant when the underlying model is an embedding model.
      - `caching` Caching — Caching configuration for the model. Caching improves system efficiency by caching frequently accessed data, both at the conversational level (storing request-specific conversation history) and at the semantic level (saving the embeddings for queries and results), ensuring optimal performance while managing memory costs effectively. Supports multiple caching strategies for improved response times and reduced strain on backend LLM services.
        - `enableStandard` boolean — Enables standard caching using exact match caching with SHA-256 hash of the prompt request/query as the document key. Returns cached response if hash matches, otherwise stores the new response with the SHA-256 hash as the key. Ideal for identical repeated requests.
        - `enableConversational` boolean — Enables conversational caching for maintaining conversation history and context for both standard and semantic caching strategies. This enables contextual session-based caching where conversation context (session topic) is stored along with either standard or semantic cache. Allows searching entire conversations for matches and can return all conversations for a given context/session or only specific matched responses. Essential for maintaining conversation history and context.
        - `semantic` object — Semantic caching configuration that enables similarity-based caching using Couchbase FTS vector search. Creates embeddings for prompt queries, performs vector search with configurable score threshold, and returns cached responses for semantically similar requests. Semantic caching is enabled by the presence of this object.
          - `embeddingModel` string — Specifies the embedding model deployed by the customer to use for generating vector embeddings. This model converts text queries into numerical vectors for semantic similarity matching in the cache.
          - `scoreThreshold` number — The threshold value for semantic similarity matching, should be > 0. Default is 0.75.
          - `dimensions` integer — The vector dimensions for semantic caching.
          - `distanceMetric` string — The vector similarity metric used for semantic matching.
        - `defaultCache` 'standard' | 'semantic' — Specifies the primary caching strategy when multiple types are enabled. Choose 'standard' for exact SHA-256 hash matching or 'semantic' for vector similarity-based matching as the default behavior.
        - `expiryTTL` integer — Cache expiry time-to-live (TTL) in seconds. Determines how long cached responses, embeddings, and conversation context remain valid before being automatically removed from the cache store.
      - `enableBatching` boolean — Enables batch processing to provide cost savings and improved efficiency for users making multiple similar large volume requests. When enabled, the system groups requests together and processes them in bulk, resulting in lower inference costs and better resource utilization. Note that batching is good for processing large volumes of requests asynchronously, but it can have delayed results (no streaming), lack of real-time feedback, limited debugging visibility, and a longer turnaround time, hence unsuitable for latency-sensitive use cases. Users can check the status of their batches or cancel an ongoing batch using the AI gateway APIs for batching.
      - `keywordFiltering` string[] — Keywords in a comma-separated string to filter the input.
    - `cloudConfig` CloudConfig — The cloud configuration for the model.
      - `provider` 'aws' | 'gcp' | 'azure', required — The cloud service provider where the model will be deployed. Currently only AWS is supported.
      - `region` string, required — Cloud provider region, for example `us-west-2`.
      - `compute` object, required — Type of the compute on which the model is deployed.
        - `cpu` 4 | 32, required — The number of cpu vCPUs. For AWS instances g6.xlarge, g6e.xlarge use 4 vCPUs, and for p3.8xlarge use 32 vCPUs.
        - `gpuMemory` 24 | 48 | 192, required — The memory in GB for the GPU. For AWS instance g6.xlarge use 24 GB GPU Memory, for g6e.xlarge use 48 GB GPU Memory, and for g6e.12xlarge use 192 GB RAM.
    - `status` string — Current status of the deployed model. Would be one of the following - deploying, destroying, deployFailed, destroyFailed, pausing, pauseFailed, paused, resuming, resumeFailed.
    - `usageMetrics` UsageMetrics — Token and request information.
      - `tokens` object — Details about the tokens consumed by the model.
        - `value` integer — The number of tokens consumed by the model.
        - `trend` 'increasing' | 'decreasing' — The trend of token consumption.
      - `requests` object — The requests consumed by the model.
        - `value` integer — The number of requests consumed by the model.
        - `trend` 'increasing' | 'decreasing' — The trend of request consumption.
    - `connectionString` string — The endpoint URL for the model.
    - `audit` CouchbaseAuditData
      - `createdBy` string, required — The user who created the resource; this will be a UUID4 ID for standard users and will be a string such as "internal-support" for internal Couchbase support users.
      - `createdAt` string, date-time, required — The RFC3339 timestamp associated with when the resource was initially created.
      - `modifiedBy` string, required — The user who last modified the resource; this will be a UUID4 ID for standard users and will be a string such as "internal-support" for internal Couchbase support users.
      - `modifiedAt` string, date-time, required — The RFC3339 timestamp associated with when the resource was last modified.
      - `version` integer, required — The version of the document. This value is incremented each time the resource is modified.
    - `actions` string[] — Actions that can be performed on the language model.

## Other responses

- `403` — The client does not have the necessary permissions to access this resource.
- `404` — The requested resource was not found.
- `422` — Request validation error.
- `429` — Returned when the client exceeds the rate limit for the given APIKey.
- `500` — An unexpected error occurred in the server while processing this request.

---

[API](https://skmtc.net/couchbase/apis/couchbase-capella-management-api.md) · [All operations](https://skmtc.net/couchbase/apis/couchbase-capella-management-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/couchbase/couchbase-capella-management-api/revisions/27d3c1e98fee/schema)