List models | Respan Docs

array: A list of models.

Example

1 {
2     "models": [
3        {
4         "model_name":"gpt-3.5-turbo",
5         "max_context_window":4096,
6         "input_cost":0.5,
7         "output_cost":0.1,
8         "rate_limit":30000,
9         "provider": {
10             "provider_name": "OpenAI",
11             "provider_id": "openai",
12             "moderation": "Filtered",
13             "credential_fields": [
14                 "api_key" // The API key for the provider
15             ]
16         }
17        },
18        // ... other models ... 
19     ]
20 }

Model parameters

string: The name used in model parameter for calling the Respan chat completion endpoint.
number: The maximum number of tokens the model can process in one API call.
number: Cost in US dollars for 1 million input tokens.
number: Cost in US dollars for 1 million output tokens.
number: The rate limit for calling this model with Respan.
object: The provider of the model.

Properties

string: The name of the provider.
string: The ID of the provider.
string: The moderation level of the provider. Possible values: Filtered, Unfiltered.
array: The fields required to authenticate with the provider.

1 {
2     "models": [
3        {
4         "model_name":"gpt-3.5-turbo",
5         "max_context_window":4096,
6         "input_cost":0.5,
7         "output_cost":0.1,
8         "rate_limit":30000,
9         "provider": {
10             "provider_name": "OpenAI",
11             "provider_id": "openai",
12             "moderation": "Filtered",
13             "credential_fields": [
14                 "api_key" // The API key for the provider
15             ]
16         }
17        },
18        // ... other models ... 
19     ]
20 }

- *array*: A list of models. **Example** ```json { "models": [ { "model_name":"gpt-3.5-turbo", "max_context_window":4096, "input_cost":0.5, "output_cost":0.1, "rate_limit":30000, "provider": { "provider_name": "OpenAI", "provider_id": "openai", "moderation": "Filtered", "credential_fields": [ "api_key" // The API key for the provider ] } }, // ... other models ... ] } ``` ## Model parameters - *string*: The name used in `model` parameter for calling the Respan [chat completion](/api-reference/develop/gateway/create-chat-completion) endpoint. - *number*: The maximum number of tokens the model can process in one API call. - *number*: Cost in US dollars for 1 million input tokens. - *number*: Cost in US dollars for 1 million output tokens. - *number*: The rate limit for calling this model with Respan. - *object*: The provider of the model. **Properties** - *string*: The name of the provider. - *string*: The ID of the provider. - *string*: The moderation level of the provider. Possible values: `Filtered`, `Unfiltered`. - *array*: The fields required to authenticate with the provider. ```json { "models": [ { "model_name":"gpt-3.5-turbo", "max_context_window":4096, "input_cost":0.5, "output_cost":0.1, "rate_limit":30000, "provider": { "provider_name": "OpenAI", "provider_id": "openai", "moderation": "Filtered", "credential_fields": [ "api_key" // The API key for the provider ] } }, // ... other models ... ] } ```

Authentication

AuthorizationBearer

API key authentication. Get your API key from https://platform.respan.ai/platform/api-keys

Response

Successful response for List models

Errors

401

Unauthorized Error

array: A list of models.

Example

1 {
2     "models": [
3        {
4         "model_name":"gpt-3.5-turbo",
5         "max_context_window":4096,
6         "input_cost":0.5,
7         "output_cost":0.1,
8         "rate_limit":30000,
9         "provider": {
10             "provider_name": "OpenAI",
11             "provider_id": "openai",
12             "moderation": "Filtered",
13             "credential_fields": [
14                 "api_key" // The API key for the provider
15             ]
16         }
17        },
18        // ... other models ... 
19     ]
20 }

Model parameters

string: The name used in model parameter for calling the Respan chat completion endpoint.
number: The maximum number of tokens the model can process in one API call.
number: Cost in US dollars for 1 million input tokens.
number: Cost in US dollars for 1 million output tokens.
number: The rate limit for calling this model with Respan.
object: The provider of the model.

Properties

string: The name of the provider.
string: The ID of the provider.
string: The moderation level of the provider. Possible values: Filtered, Unfiltered.
array: The fields required to authenticate with the provider.

1 {
2     "models": [
3        {
4         "model_name":"gpt-3.5-turbo",
5         "max_context_window":4096,
6         "input_cost":0.5,
7         "output_cost":0.1,
8         "rate_limit":30000,
9         "provider": {
10             "provider_name": "OpenAI",
11             "provider_id": "openai",
12             "moderation": "Filtered",
13             "credential_fields": [
14                 "api_key" // The API key for the provider
15             ]
16         }
17        },
18        // ... other models ... 
19     ]
20 }

1	import requests
2
3	url = "https://api.respan.ai/api/models/public"
4
5	headers = {"Authorization": "Bearer <token>"}
6
7	response = requests.get(url, headers=headers)
8
9	print(response.json())

1	{
2	"models": [
3	{
4	"model_name":"gpt-3.5-turbo",
5	"max_context_window":4096,
6	"input_cost":0.5,
7	"output_cost":0.1,
8	"rate_limit":30000,
9	"provider": {
10	"provider_name": "OpenAI",
11	"provider_id": "openai",
12	"moderation": "Filtered",
13	"credential_fields": [
14	"api_key" // The API key for the provider
15	]
16	}
17	},
18	// ... other models ...
19	]
20	}