Models

Token360 gives you access to supported models through a single API. You don't need to manage individual provider accounts.

Model List

How Model Selection Works

When you send a request, set model to the model name you want to use, such as glm-5.1 or dola-seed-2.0-pro.

Token360 handles authentication, availability, and usage metering for the request. If a model is unavailable, the API returns a standard error response.

Using a Specific Model

Simply pass the model name in your API request:

1# Zhipu AI model
2curl https://api.token360.ai/v1/chat/completions \
3  -H "Authorization: Bearer sk-your-api-key" \
4  -H "Content-Type: application/json" \
5  -d '{"model": "glm-5.1", "messages": [{"role": "user", "content": "Hello!"}]}'
6
7# Byteplus model
8curl https://api.token360.ai/v1/chat/completions \
9  -H "Authorization: Bearer sk-your-api-key" \
10  -H "Content-Type: application/json" \
11  -d '{"model": "dola-seed-2.0-pro", "messages": [{"role": "user", "content": "Hello!"}]}'

Listing Available Models

Use the public Models API to browse available models:

1curl 'https://api.token360.ai/public/models?size=20&current=1' \
2  -H "Authorization: Bearer sk-your-api-key"

Without query params, it defaults to page 1 with page size 10.