Tokenless
G
OpenAI

o4-mini API at half of list price

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.

ReasoningCodingVisionTool use

o4-mini API pricing

Every rate is 50% of the provider's official list price. USD per million tokens.

Token typeList priceTokenless
Input$1.10$0.55
Output$4.40$2.20
Cache write$1.10$0.55
Cache read$0.28$0.14

Call o4-mini in one request

Tokenless speaks the OpenAI Chat Completions format. Point your client at the base URL, set model to o4-mini, and you are done.

request.sh
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" }]
  }'

More GPT models