Sign in
v1
v1

Get Model

Get information about a specific model.

Returns detailed information about a specific model by ID. The model must be available to your API key's configured providers.

Args: model_id: The ID of the model to retrieve (e.g., 'openai/gpt-4', 'anthropic/claude-3-5-sonnet-20241022') user: Authenticated user obtained from API key validation

Returns: DedalusModel: Information about the requested model

Raises: HTTPException: - 401 if authentication fails - 404 if model not found or not accessible with current API key - 500 if internal error occurs

Requires: Valid API key with 'read' scope permission

Example: ```python import dedalus_labs

client = dedalus_labs.Client(api_key="your-api-key")
model = client.models.retrieve("openai/gpt-4")

print(f"Model: {model.id}")
print(f"Owner: {model.owned_by}")
```

Response:
```json
{
    "id": "openai/gpt-4",
    "object": "model",
    "created": 1687882411,
    "owned_by": "openai"
}
```
get/v1/models/{model_id}

Path parameters

model_idstring required

Response

Successful Response

idstring required

Model identifier

createdinteger

Unix timestamp of model creation

objectstring

Object type, always 'model'

owned_bystring

Organization that owns this model

namestring nullable

Model name (alias for id)

temperaturenumber nullable

Sampling temperature (0 to 2). Higher values make output more random.

top_pnumber nullable

Nucleus sampling parameter. Alternative to temperature.

frequency_penaltynumber nullable

Penalize new tokens based on their frequency in the text so far.

presence_penaltynumber nullable

Penalize new tokens based on whether they appear in the text so far.

max_tokensinteger nullable

Maximum number of tokens to generate.

max_completion_tokensinteger nullable

An upper bound for the number of tokens that can be generated for a completion.

ninteger nullable

Number of completions to generate for each prompt.

streamboolean nullable

Whether to stream back partial progress.

stream_optionsobject nullable

Options for streaming responses.

logit_biasobject nullable

Modify the likelihood of specified tokens appearing.

logprobsboolean nullable

Whether to return log probabilities of the output tokens.

top_logprobsinteger nullable

Number of most likely tokens to return at each token position.

response_formatobject nullable

Format for the model output (e.g., {'type': 'json_object'}).

seedinteger nullable

Seed for deterministic sampling.

service_tierstring nullable

Latency tier for the request (e.g., 'auto', 'default').

toolsobject[] nullable

List of tools the model may call.

parallel_tool_callsboolean nullable

Whether to enable parallel function calling.

userstring nullable

A unique identifier representing your end-user.

attributesobject nullable

[Dedalus] Custom attributes for intelligent model routing (e.g., intelligence, speed, creativity, cost).

metadataobject nullable

[Dedalus] Additional metadata for request tracking and debugging.

Changes