The latest Fable, built for demanding reasoning and long-horizon agentic work across a 1M-token context, with adaptive thinking always on. It lists below Fable 5.1, making it the default choice for the hardest work.
Every rate is 50% of the provider's official list price. USD per million tokens.
| Token type | List price | Tokenless |
|---|---|---|
| Input | $8.00 | $4.00 |
| Output | $40.00 | $20.00 |
| Cache write (5 min) | $10.00 | $5.00 |
| Cache write (1 hour) | $16.00 | $8.00 |
| Cache read | $0.20 | $0.10 |
Tokenless speaks the OpenAI Chat Completions format. Point your client at the base URL, set model to fable-5.2, 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": "fable-5.2",
"messages": [{ "role": "user", "content": "Hello" }]
}'On Tokenless, Claude Fable 5.2 costs $4.00 per million input tokens and $20.00 per million output tokens, half of Anthropic's list price of $8.00 and $40.00.
Yes. Tokenless routes a request for fable-5.2 to the genuine Claude Fable 5.2 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 fable-5.2. You pay per token from a prepaid balance, and your first $1 is free.
Claude Fable 5.2 accepts up to 1,000,000 tokens of context and returns up to 128,000 output tokens per request.