OpenAI's latest Instant model as used in ChatGPT, with a 400K-token context and tool calling. The underlying snapshot is updated regularly, so behavior can shift between updates; pin a GPT-6 model when you need stable output.
Every rate is 50% of the provider's official list price. USD per million tokens.
| Token type | List price | Tokenless |
|---|---|---|
| Input | $5.00 | $2.50 |
| Output | $30.00 | $15.00 |
| Cache write | $5.00 | $2.50 |
| Cache read | $0.50 | $0.25 |
Tokenless speaks the OpenAI Chat Completions format. Point your client at the base URL, set model to chat-latest, 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": "chat-latest",
"messages": [{ "role": "user", "content": "Hello" }]
}'