Set Model

PUThttps://api.confident-ai.com/v2/projects/{projectId}/models/{modelType}

Sets one of the project's models, selected by the modelType path segment. evaluation configures the LLM judge that scores this project's metrics. platform configures the model behind Confident AI's own AI features, like classification, summaries and report generation. simulation configures the model that simulates user turns in conversation simulations, including multi-turn test runs and red teaming. Setting platform or simulation creates a project override, so the project stops following the organization's default and source becomes project; remove it with the DELETE method to fall back to that default.

The provider's credential must already be configured on the project or the organization; set it first through the model credentials endpoints. A provider your organization's model provider policy does not allow is rejected with a 403. CONFIDENT_AI needs no credential and stores a null model name. maxInputTokens applies to the platform and simulation models only and is rejected on the evaluation path.

PUT/v2/projects/{projectId}/models/{modelType}

curl -X PUT "https://api.confident-ai.com/v2/projects/{projectId}/models/{modelType}" \
  -H "CONFIDENT_API_KEY: <ORGANIZATION-API-KEY>" \
  -H "Content-Type: application/json" \
  -d '{
  "provider": "OPEN_AI",
  "name": "gemini-2.0-flash",
  "maxConcurrency": 5
}'

200

{
  "success": true,
  "data": {
    "model": {
      "id": "<MODEL-ID>",
      "type": "EVALUATION",
      "provider": "GEMINI",
      "name": "gemini-2.0-flash",
      "maxConcurrency": 5,
      "maxInputTokens": 128000,
      "projectId": null,
      "organizationId": "<ORGANIZATION-ID>"
    },
    "source": "project"
  },
  "deprecated": false
}

Headers

CONFIDENT_API_KEYstringRequired
The organization API key for your Confident AI organization.

Path parameters

projectIdstringRequired
The id of the project, which must belong to the organization your API key is scoped to.
modelTypeenumRequired
Which of the project's models to act on.

Request body

Update Evaluation Model Requestobject
The model to run as the project's evaluation model. It takes no maxInputTokens, which is rejected on this path.
Show 3 propertiesHide 3 properties
- providerenumRequired
  This is the provider of the model.
  Show 18 enum valuesHide 18 enum values
  - OPEN_AI
  - CUSTOM
  - CONFIDENT_AI
  - BEDROCK
  - ANTHROPIC
  - GEMINI
  - X_AI
  - DEEPSEEK
  - MOONSHOT_AI
  - VERTEX_AI
  - AZURE
  - MISTRAL
  - PERPLEXITY
  - OPEN_ROUTER
  - PORTKEY
  - LITE_LLM
  - TRUE_FOUNDRY
  - HUGGING_FACE
- namestring
  The model to call at that provider, for example gemini-2.0-flash. Omit it to fall back to the provider's default; it is ignored for CONFIDENT_AI, which always stores a null name. A Portkey model must be written as the saved integration slug, for example @openai-prod/gpt-4o.
- maxConcurrencyinteger | null
  How many calls Confident AI may make to this model at once. Omit it or send null for no limit of its own.
OR
Update Platform Model Requestobject
The model to run for any project model type other than evaluation.
Show 4 propertiesHide 4 properties
- providerenumRequired
  This is the provider of the model.
  Show 18 enum valuesHide 18 enum values
  - OPEN_AI
  - CUSTOM
  - CONFIDENT_AI
  - BEDROCK
  - ANTHROPIC
  - GEMINI
  - X_AI
  - DEEPSEEK
  - MOONSHOT_AI
  - VERTEX_AI
  - AZURE
  - MISTRAL
  - PERPLEXITY
  - OPEN_ROUTER
  - PORTKEY
  - LITE_LLM
  - TRUE_FOUNDRY
  - HUGGING_FACE
- namestring
  The model to call at that provider, for example gemini-2.0-flash. Omit it to fall back to the provider's default; it is ignored for CONFIDENT_AI, which always stores a null name. A Portkey model must be written as the saved integration slug, for example @openai-prod/gpt-4o.
- maxConcurrencyinteger | null
  How many calls Confident AI may make to this model at once. Omit it or send null for no limit of its own.
- maxInputTokensinteger | null
  How many input tokens Confident AI may send to this model per call. The platform, simulation and speech models only: sending it on the evaluation path is rejected. Omit it or send null for no limit of its own.

Response

Set Model succeeded.

successboolean
Indicates if the request was successful.
dataobject
The project's model as it now stands. source is returned for the platform and simulation models, where the write creates a project override and so answers which scope now wins; the evaluation model is always project scoped and omits it.
Show 2 propertiesHide 2 properties
- modelobject
  One model configuration: the provider and model Confident AI calls for a given purpose, with the limits it calls them under. A configuration belongs either to the organization (organizationId set) or to a single project (projectId set), never to both.
  Show 8 propertiesHide 8 properties
  - idstring
    The id of the model configuration, generated by Confident AI.
  - typeenum
    What a configured model is used for. EVALUATION is the LLM judge that scores a project's metrics, PLATFORM is the model behind Confident AI's own AI features such as classification, summaries and report generation, and SIMULATION is the model that simulates user turns in conversation simulations. Those three are the only types the public API reads or writes.
    Show 6 enum valuesHide 6 enum values
    EVALUATION
    PLATFORM
    GENERATION
    SIMULATION
    TEXT_TO_SPEECH
    SPEECH_TO_TEXT
  - providerenum | null
    This is the provider of the model.
    Show 18 enum valuesHide 18 enum values
    OPEN_AI
    CUSTOM
    CONFIDENT_AI
    BEDROCK
    ANTHROPIC
    GEMINI
    X_AI
    DEEPSEEK
    MOONSHOT_AI
    VERTEX_AI
    AZURE
    MISTRAL
    PERPLEXITY
    OPEN_ROUTER
    PORTKEY
    LITE_LLM
    TRUE_FOUNDRY
    HUGGING_FACE
  - namestring | null
    The model to call at that provider, or null when the provider's default is used. Always null for CONFIDENT_AI.
  - maxConcurrencyinteger | null
    How many calls Confident AI makes to this model at once, or null for no limit of its own.
  - maxInputTokensinteger | null
    How many input tokens Confident AI sends to this model per call, or null for no limit of its own.
  - projectIdstring | null
    The id of the project this configuration overrides the organization default for, or null when it is the organization default itself.
  - organizationIdstring | null
    The id of the organization this configuration is the default for, or null when it is a project override.
- sourceenum
  Where the model in effect for a project comes from: project when the project has an override of its own, organization when it follows the organization's default. The evaluation model is always project scoped, so it only ever reports project.
  Show 2 enum valuesHide 2 enum values
  - project
  - organization
deprecatedboolean
Indicates if this endpoint is deprecated.

Built byConfident AI