A cost-efficient step below Sol, built for the bulk of production traffic that needs solid reasoning and coding without flagship pricing.
Every rate is 50% of the provider's official list price. USD per million tokens.
| Token type | List price | Tokenless |
|---|---|---|
| Input | $2.00 | $1.00 |
| Output | $12.00 | $6.00 |
| Cache write | $2.50 | $1.25 |
| Cache read | $0.20 | $0.10 |
| Prompts over 272K tokens | ||
| Input | $4.00 | $2.00 |
| Output | $18.00 | $9.00 |
| Cache write | $5.00 | $2.50 |
| Cache read | $0.40 | $0.20 |
A request whose prompt, including cached tokens, is over the threshold is billed entirely at the long-prompt rates, as the provider bills it.
Tokenless speaks the OpenAI Chat Completions format. Point your client at the base URL, set model to gpt-5.6-terra, and you are done.
curl https://api.tokenless.store/api/v1/chat/completions \
-H "Authorization: Bearer $TOKENLESS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.6-terra",
"messages": [{ "role": "user", "content": "Hello" }]
}'On Tokenless, GPT-5.6 Terra costs $1.00 per million input tokens and $6.00 per million output tokens, half of OpenAI's list price of $2.00 and $12.00. Prompts over 272K tokens bill at $2.00 input and $9.00 output per million.
Yes. Tokenless routes a request for gpt-5.6-terra to the genuine GPT-5.6 Terra and returns its response unchanged. No cheaper model is substituted.
Point any OpenAI-compatible SDK at https://api.tokenless.store/api/v1, use your Tokenless API key, and set the model to gpt-5.6-terra. You pay per token from a prepaid balance, and your first $1 is free.
GPT-5.6 Terra accepts up to 1,050,000 tokens of context and returns up to 128,000 output tokens per request.