OpenAI's latest small reasoning model, with low latency and high quality on coding, math, and science, with vision support. A cost-efficient default for reasoning-heavy tasks that still need to be quick.
Every rate is 50% of the provider's official list price. USD per million tokens.
| Token type | List price | Tokenless |
|---|---|---|
| Input | $1.10 | $0.55 |
| Output | $4.40 | $2.20 |
| Cache write | $1.10 | $0.55 |
| Cache read | $0.28 | $0.14 |
Tokenless speaks the OpenAI Chat Completions format. Point your client at the base URL, set model to o4-mini, 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": "o4-mini",
"messages": [{ "role": "user", "content": "Hello" }]
}'