OpenAI API Response Reference¶
This document contains reference responses from the OpenAI API for comparison with Continuum Router's extended responses.
GET /v1/models¶
The OpenAI /v1/models endpoint returns a list of available models with minimal metadata.
Response Format¶
{
"object": "list",
"data": [
{
"id": "gpt-4o",
"object": "model",
"created": 1715367049,
"owned_by": "system"
},
{
"id": "gpt-4o-mini",
"object": "model",
"created": 1721172741,
"owned_by": "system"
},
{
"id": "gpt-4-turbo",
"object": "model",
"created": 1712361441,
"owned_by": "system"
},
{
"id": "gpt-4-0613",
"object": "model",
"created": 1686588896,
"owned_by": "openai"
},
{
"id": "gpt-3.5-turbo",
"object": "model",
"created": 1677610602,
"owned_by": "openai"
},
{
"id": "dall-e-3",
"object": "model",
"created": 1698785189,
"owned_by": "system"
},
{
"id": "dall-e-2",
"object": "model",
"created": 1698798177,
"owned_by": "system"
},
{
"id": "whisper-1",
"object": "model",
"created": 1677532384,
"owned_by": "openai-internal"
},
{
"id": "tts-1",
"object": "model",
"created": 1681940951,
"owned_by": "openai-internal"
},
{
"id": "tts-1-hd",
"object": "model",
"created": 1699053533,
"owned_by": "system"
},
{
"id": "text-embedding-ada-002",
"object": "model",
"created": 1671217299,
"owned_by": "openai-internal"
},
{
"id": "text-embedding-3-small",
"object": "model",
"created": 1705948997,
"owned_by": "system"
},
{
"id": "text-embedding-3-large",
"object": "model",
"created": 1705953180,
"owned_by": "system"
}
]
}
Field Descriptions¶
| Field | Type | Description |
|---|---|---|
id | string | The model identifier (e.g., "gpt-4o", "dall-e-3") |
object | string | Always "model" |
created | integer | Unix timestamp of when the model was created |
owned_by | string | The organization that owns the model ("openai", "system", "openai-internal") |
Key Observations¶
- No Capability Information: The OpenAI API does not include any capability information in the
/v1/modelsresponse. Clients must rely on: - Model naming conventions (e.g., "dall-e" for image generation)
- External documentation
-
Trial and error
-
Minimal Metadata: Only basic identification and timestamp fields are provided.
-
No Context Window Information: Maximum token limits are not included in the response.
-
No Pricing Information: Cost per token is not available through this endpoint.
Continuum Router Extension¶
Continuum Router extends the standard OpenAI response with additional metadata from model-metadata.yaml:
{
"object": "list",
"data": [
{
"id": "gpt-4o",
"object": "model",
"created": 1715367049,
"owned_by": "system",
"metadata": {
"display_name": "GPT-4o",
"developer": "OpenAI",
"summary": "Most advanced multimodal model with vision capabilities",
"capabilities": ["chat", "vision", "function_calling", "code"],
"limits": {
"context_window": 128000,
"max_output": 16384
}
}
},
{
"id": "dall-e-3",
"object": "model",
"created": 1698785189,
"owned_by": "system",
"metadata": {
"display_name": "DALL-E 3",
"developer": "OpenAI",
"summary": "High quality image generation with detailed prompt understanding",
"capabilities": ["image_generation"],
"limits": {
"context_window": 0,
"max_output": 0,
"max_prompt_length": 4000
}
}
}
]
}
Extended Fields¶
| Field | Type | Description |
|---|---|---|
metadata.display_name | string | Human-readable model name |
metadata.developer | string | Company/organization that developed the model |
metadata.summary | string | Brief description of the model's purpose |
metadata.capabilities | array | List of model capabilities (see below) |
metadata.limits.context_window | integer | Maximum context window in tokens |
metadata.limits.max_output | integer | Maximum output tokens |
Capability Values¶
See model-metadata.yaml for the complete list of standardized capability values:
- Text/Chat:
chat,reasoning,code,function_calling,tool - Multimodal Input:
vision,audio,video - Generation:
image_generation,image_edit,image_variation - Other:
embedding,moderation
GET /v1/models/{model}¶
Retrieve information about a specific model.
Request¶
Response¶
The same minimal fields are returned for individual model lookups.