Retrieve a model

GET

https://api.respan.ai/api/models/:model_name/

GET

/api/models/:model_name/

$ curl https://api.respan.ai/api/models/model_name/ \
>      -H "Authorization: Bearer <respanApiKey>"

1 {
2   "id": "my-custom-gpt-4o",
3   "model_name": "my-custom-gpt-4o",
4   "is_officially_supported": true,
5   "display_name": "My Custom GPT-4o",
6   "base_model_name": "gpt-4o",
7   "affiliation_category": "custom",
8   "is_called_by_custom_name": false,
9   "input_cost": 2.5,
10   "output_cost": 10,
11   "cache_hit_input_cost": 0.5,
12   "cache_creation_input_cost": 3,
13   "max_context_window": 128000,
14   "streaming_support": 1,
15   "function_call": 1,
16   "image_support": 1,
17   "source": "db",
18   "model_type": "chat",
19   "supported_params": {},
20   "throughput": {
21     "average_tps": 1.1,
22     "average_ttft": 1.1,
23     "average_latency": 1.1,
24     "number_of_requests": 1
25   },
26   "provider": {
27     "id": "my-vllm",
28     "provider_id": "my-vllm",
29     "provider_name": "My vLLM Server",
30     "extra_kwargs": {
31       "base_url": "https://vllm.example.com/v1"
32     },
33     "created_at": "2024-01-15T09:30:00Z",
34     "updated_at": "2024-01-15T09:30:00Z"
35   },
36   "created_at": "2024-01-15T09:30:00Z",
37   "updated_at": "2024-01-15T09:30:00Z"
38 }

Retrieve a built-in or custom model by model name. Custom models are only visible to the owning organization.

Authentication

AuthorizationBearer

Use your Respan API key for Respan API authentication. Enter only the Respan API key value; clients send Authorization: Bearer <RESPAN_API_KEY>. For /api/responses, provider credentials such as Perplexity, OpenAI, or Azure OpenAI go in Settings -> Providers or respan_params.credential_override in the request body, not in this authentication field.

AuthorizationBearer

Use a dashboard JWT only for dashboard-authenticated endpoints. Respan API-key endpoints use the respanApiKey auth field instead.

Path parameters

model_namestringRequired

Model name. The route supports names containing slashes, such as openai/gpt-4o-mini.

Response

Model details.

idstring

Model string ID. Same value as model_name.

model_namestring

Model name used in API calls.

is_officially_supportedbooleanRead-only

Whether the model’s bare slug is in Respan’s first-party supported catalog.

display_namestringOptional

Human-readable model name.

base_model_namestringOptional

Base model inherited from, when configured.

affiliation_categoryenumOptional

Whether the model is built in or organization-specific.

is_called_by_custom_namebooleanOptional

Whether requests are sent upstream using this custom model name.

input_costdoubleOptional

Cost per 1M input tokens in USD.

output_costdoubleOptional

Cost per 1M output tokens in USD.

cache_hit_input_costdoubleOptional

Cost per 1M cached input tokens in USD.

cache_creation_input_costdoubleOptional

Cost per 1M cache creation input tokens in USD.

max_context_windowintegerOptional

Maximum context window size.

streaming_supportenumOptional

Streaming support. 0 = no, 1 = yes.

function_callenumOptional

Function/tool calling support. 0 = no, 1 = yes.

image_supportenumOptional

Vision input support. 0 = no, 1 = yes.

sourceenumOptional

Source of the model definition.

model_typeenumOptional

Model type.

supported_paramsmap from strings to anyOptional

Computed parameter support after applying model-specific overrides.

throughputobject or nullOptional

providerobjectOptional

created_atdatetime or nullOptional

updated_atdatetime or nullOptional

Errors

401

Unauthorized Error

404

Not Found Error