Quickstart

Get your first AI response through Token360 in under 2 minutes.

Prerequisites

• A Token360 account (sign up here)

Step 1: Get Your API Key

1. Log in to the Token360 Console.
2. Navigate to API Keys in the sidebar.
3. Click Create API Key, give it a name, and copy the key.

Your key starts with sk- and looks like: sk-abc123def456...

Important: Store your API key securely. It will only be shown once.

Step 2: Top Up Your Account

Before making API calls, you need to add funds to your account.

1. Click your profile avatar in the top-right corner.
2. Select Wallet from the dropdown menu.
3. On the Wallet page, click the Add Funds button under the "Add Funds" section.
4. Follow the payment instructions to complete your top-up using Stripe or credit card.

Tip: Your available balance will be shown on the Wallet page. You can return here anytime to check your balance or add more funds.

Step 3: Send Your First Request

The examples below use Claude Opus 5 (claude-opus-5), a production catalog LLM. Swap the model field for any name from Models.

1curl https://api.token360.ai/v1/chat/completions \
2  -H "Authorization: Bearer sk-your-api-key" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "model": "claude-opus-5",
6    "messages": [
7      {"role": "user", "content": "Hello! What can you do?"}
8    ]
9  }'

Step 4: Verify the Response

A successful response looks like:

1{
2  "id": "chatcmpl-abc123",
3  "object": "chat.completion",
4  "created": 1677652288,
5  "model": "claude-opus-5",
6  "choices": [
7    {
8      "index": 0,
9      "message": {
10        "role": "assistant",
11        "content": "Hello! I'm an AI assistant. I can help you with..."
12      },
13      "finish_reason": "stop"
14    }
15  ],
16  "usage": {
17    "prompt_tokens": 12,
18    "completion_tokens": 25,
19    "total_tokens": 37
20  }
21}

Optional: Image and video

Same API key. Different endpoints and model IDs from the production catalog:

1curl https://api.token360.ai/v1/images/generations \
2  -H "Authorization: Bearer sk-your-api-key" \
3  -H "Content-Type: application/json" \
4  -d '{"model":"nano-banana-pro","prompt":"A minimalist sunrise over calm water"}'
5
6curl https://api.token360.ai/v1/videos \
7  -H "Authorization: Bearer sk-your-api-key" \
8  -H "Content-Type: application/json" \
9  -d '{"model":"seedance-2.5","prompt":"A serene Japanese garden with falling cherry blossoms","resolution":"720p"}'

Video is asynchronous: poll GET /v1/videos/{id} (or set callback_url — see Webhook). Image generation returns the result in the same response.

Optional: Async Chat

Queue one non-streaming chat completion and poll the job. Billing matches synchronous chat (including enterprise price factor). There is no callback_url on this API.

1curl -X POST https://api.token360.ai/v1/async/chat/completions \
2  -H "Authorization: Bearer sk-your-api-key" \
3  -H "Content-Type: application/json" \
4  -d '{"model":"claude-opus-5","messages":[{"role":"user","content":"Say hi in one word."}],"stream":false}'

Full guide: Async Chat.

Optional: Batch jobs

For many chat completion requests in one JSONL file, use the OpenAI-compatible Batch API. Platform execution bills at the same rates as sync chat (enterprise factor included; no extra 50% batch discount). Provider-native Batch Infer may apply a batch discount when that route exists.

1. Call GET /v1/batches/models for models you can submit to POST /v1/batches (supports_provider_batch means an upstream Infer route also exists — it is often false).
2. Build a .jsonl file (one POST /v1/chat/completions request per line; same body.model on every line).
3. POST /v1/files with purpose=batch, then POST /v1/batches with input_file_id (optional execution and callback_url).
4. Poll GET /v1/batches/{batch_id} or configure a webhook.

1curl https://api.token360.ai/v1/batches/models \
2  -H "Authorization: Bearer sk-your-api-key"
3
4curl https://api.token360.ai/v1/files -H "Authorization: Bearer sk-your-api-key" \
5  -F purpose=batch -F file=@requests.jsonl
6
7curl -X POST https://api.token360.ai/v1/batches \
8  -H "Authorization: Bearer sk-your-api-key" \
9  -H "Content-Type: application/json" \
10  -d '{"input_file_id":"file_...","endpoint":"/v1/chat/completions","completion_window":"24h","execution":"platform"}'

Full guide: Batch Jobs.