OpenAI's most cost-efficient model — ideal for classification, routing, extraction, and other lightweight tasks where speed and low cost matter most.
Every rate is 50% of the provider's official list price. USD per million tokens.
| Token type | List price | Tokenless |
|---|---|---|
| Input | $0.20 | $0.10 |
| Output | $1.25 | $0.63 |
| Cache write | $0.20 | $0.10 |
| Cache read | $0.02 | $0.01 |
Tokenless speaks the OpenAI Chat Completions format. Point your client at the base URL, set model to gpt-5.4-nano, 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-5.4-nano",
"messages": [{ "role": "user", "content": "Hello" }]
}'