Models

List the AI models available to your account, including pricing, provider information, and technical specifications.

Method and endpoint	POST {API_URL}/models
Base URL (API_URL)	https://gpu-api.exascalelabs.ai/api/v1
Authentication	Bearer access token with refresh-token, or a Bearer API token
Returns	A list of models with pricing, provider, and capability details

HTTP Request

GET {API_URL}/models

A models request: your application calls the endpoint with a Bearer token, and the Token Factory returns the model list.

Query string parameters

Parameters	Requirements	Type	Description
limit	Optional	int	The number of items to return
offset	Optional	int	The number of items to skip before starting to collect the result set
sortField	Optional	string	The field by which the data will be ordered
sortOrder	Optional	string	Sorting order: desc、asc

How limit, offset, sortField, and sortOrder window and order the result set.

Response Attributes

The top-level response contains the following fields:

Field	Type	Description
status	boolean	The status of the request. true signifies success, while false indicates an error.
message	string	A message describing the status of the request.
total	int	Total records count.
data	object	An array of objects, each containing details about a model.

Each entry in the data array includes the following properties:

Field	Type	Description	Example
model_name	string	Name of the model.	MiniMaxAI/MiniMax-M2.7
display_name	string	Display name of the model.	MiniMaxAI/MiniMax-M2.7
provider	object	The provider of the model (for example, OpenAI, DeepSeek, Qwen). Contains details about the provider.	{ "name": "OpenAI" }
input_tokens_price	object	Price per million input (prompt) tokens.	{ "usd": 0.03 }
output_tokens_price	object	Price per million output (completion) tokens.	{ "usd": 0.06 }
hf_repo	string	Hugging Face repository identifier.	meta-llama/Llama-2-7b
context_length	int	Maximum context length in tokens.	4095
max_completion_tokens	int	Maximum completion length in tokens.	2048
canonical_slug	string	Unique, normalized identifier used for the model.	minimaxai/minimax-m2.7
knowledge_cutoff	string	Date the training data was last updated (ISO 8601).	2024-06-01T00:00:00Z

The fields in each model entry, grouped by purpose.

The provider object

The provider field is itself an object with the following properties:

Field	Type	Description
name	string	The name of the provider (for example, OpenAI, DeepSeek, Qwen).
description	string	A brief description of the provider and its offerings.
privacy_policy_url	string	URL to the provider’s privacy policy for transparency.
terms_of_service_url	string	URL to the provider’s terms of service for user reference.
favicon_url	string	URL to the provider’s favicon for easy identification.
headquarters	string	The location of the provider’s headquarters (for example, San Francisco, CA).

The full models response structure, including the nested provider object.

Example

Request

curl -X GET '{API_URL}/models' \
-H 'Authorization: Bearer {ACCESS_TOKEN}' \
-H 'refresh-token: {REFRESH_TOKEN}' \
-H 'Content-Type: application/json'

Or, if you are using an API token:

curl -X GET '{API_URL}/models' \
-H 'Authorization: Bearer {API_TOKEN}' \
-H 'Content-Type: application/json'

Response

{
    "status": true,
    "message": "AI models retrieved successfully",
    "data": [
        {
            "id": "69fef7b5350c9599a3511fdc",
            "model_name": "MiniMaxAI/MiniMax-M2.7",
            "display_name": "MiniMaxAI/MiniMax-M2.7",
            "description": "MiniMax-M2.7 is our first model deeply participating in its own evolution. M2.7 is capable...",
            "provider": {
                "name": "Minimax",
                "description": "",
                "privacy_policy_url": "https://www.minimax.io/platform/protocol/privacy-policy",
                "terms_of_service_url": "https://www.minimax.io/platform/protocol/terms-of-service",
                "favicon_url": "https://gpu.exascalelabs.ai/logos/minimaxai.png",
                "headquarters": "SG"
            },
            "hf_repo": "MiniMaxAI/MiniMax-M2.7",
            "input_tokens_price": {
                "usd": 0.44574
            },
            "output_tokens_price": {
                "usd": 1.81815
            },
            "context_length": 4095,
            "max_completion_tokens": 4095,
            "canonical_slug": "minimaxai/minimax-m2.7",
            "knowledge_cutoff": "2024-06-01T00:00:00Z"
        }
    ],
    "total": 1
}

Code examples

The same request in Python and Node. Because the API is OpenAI-compatible, you can also use an official OpenAI SDK by pointing it at the base URL.

Python (requests)

import requests

url = "https://gpu-api.exascalelabs.ai/api/v1/models"
headers = {"Authorization": "Bearer YOUR_EXASCALE_API_TOKEN"}

resp = requests.get(url, headers=headers)
print(resp.json())

Node (fetch)

const res = await fetch("https://gpu-api.exascalelabs.ai/api/v1/models", {
    headers: { Authorization: "Bearer YOUR_EXASCALE_API_TOKEN" },
});
const data = await res.json();
console.log(data);

OpenAI SDK (Python)

from openai import OpenAI

client = OpenAI(
    base_url="https://gpu-api.exascalelabs.ai/api/v1",
    api_key="YOUR_EXASCALE_API_TOKEN",
)
models = client.models.list()
print(models)

OPENAI SDK USAGE

The SDK approach works because the endpoint follows the OpenAI API style. Treat it as compatibility-based usage and confirm any SDK-specific behavior against the documented REST contract above.

How the model list is used

This endpoint is the source of truth for the models available to your account. In the LobeChat integration, the Get Model List button calls it. In the Continue integration, you set each model’s model value to a model_name returned here.

How the Models endpoint fits into the Token Factory: the console issues tokens, Models supplies the model_name used by Chat, and Comparison draws on both.

Errors and status codes

PLACEHOLDER

This section is a placeholder. The specific HTTP status codes and the full error response body for chat requests are not yet documented here. Confirm them with the Exascale team, then complete the table.

HTTP Status	Meaning	Notes
200	Request succeeded	Returns a chat.completion object, or a steam of chunks when stream is set to true.
TBD	To be confirmed	To be supplied by Exascale.

Rate limits

PLACEHOLDER

Rate limits for this endpoint are not yet documented here. Confirm the request and token limits with the Exascale team, then complete this section.

Spending can be capped per API token using the credit limit and reset interval set when the token is created. Each user can hold up to 10 API tokens. The usage token counts returned with each response are the basis for billing.

Sources

This reference is taken from the official Exascale Cloud API documentation.

• Models (model list)
• Chat Completions