Every model. Provider price. Zero markup.

Pricing

You pay what the provider charges. Nothing more.

Every model is billed at its provider’s published per-token price: input tokens at the input rate, output tokens at the output rate. When a provider reports extra charges for a call (cached prompts, web search, reasoning), you pay that reported cost too, with no markup on any of it.

• No subscription, no seats, no monthly minimum.
• Credit is in dollars and never expires.
• Your account page shows what every call cost.

Live rates from our price list, the same table the API bills from.

Developers

Works with the OpenAI SDK you already use

TokenCenter speaks the OpenAI chat completions format. Change the base URL and the key, pick a model id from the catalog, and you’re done.

• Base URL: https://api.tokenctr.com/v1
• Endpoint: POST /chat/completions
• Auth: Authorization: Bearer <your key>
• Every response includes a usage block with token counts.

"stream": true works and returns standard OpenAI chunks; the reply arrives in one burst once it’s complete.

curl https://api.tokenctr.com/v1/chat/completions \
  -H "Authorization: Bearer $TOKENCENTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/ministral-3b-2512",
    "messages": [{"role": "user", "content": "Say hello in five words."}]
  }'