The lightweight GPT-6 model: Astra's core capabilities at a fraction of the cost, tuned for extreme speed on batch processing, summarization, extraction, and subagent tasks with a 1M-token context.
Every rate is 50% of the provider's official list price. USD per million tokens.
| Token type | List price | Tokenless |
|---|---|---|
| Input | $0.10 | $0.05 |
| Output | $0.50 | $0.25 |
| Cache write | $0.125 | $0.0625 |
| Cache read | $0.01 | $0.005 |
| Prompts over 272K tokens | ||
| Input | $0.20 | $0.10 |
| Output | $0.75 | $0.375 |
| Cache write | $0.25 | $0.125 |
| Cache read | $0.02 | $0.01 |
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-6-luna, 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-6-luna",
"messages": [{ "role": "user", "content": "Hello" }]
}'On Tokenless, GPT-6 Luna costs $0.05 per million input tokens and $0.25 per million output tokens, half of OpenAI's list price of $0.10 and $0.50. Prompts over 272K tokens bill at $0.10 input and $0.375 output per million.
Yes. Tokenless routes a request for gpt-6-luna to the genuine GPT-6 Luna 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-6-luna. You pay per token from a prepaid balance, and your first $1 is free.
GPT-6 Luna accepts up to 1,000,000 tokens of context and returns up to 128,000 output tokens per request.