All LLM prices / Anthropic
claude-fable-5 price per 1M tokens
claude-fable-5 costs $10.00 per 1M input tokens and $50.00 per 1M output tokens, and $1.00 per 1M cached input tokens read.
| Per 1M tokens | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| claude-fable-5 | $10.00 | $50.00 | $1.00 | $12.50 |
What a call costs
A typical agent step of 20,000 input and 1,500 output tokens costs $0.275 on claude-fable-5, so 10,000 of them a month is $2,750.00. Serving the repeated part of the prompt from cache cuts the input side to $1.00 per 1M, after a one-time write at $12.50.
claude-fable-5 on other providers
| Listed as | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| aihubmix/claude-fable-5 | $11.00 | $55.00 | $1.10 | $13.75 |
| anthropic.claude-fable-5 | $10.00 | $50.00 | $1.00 | $12.50 |
| apac.anthropic.claude-fable-5 | $11.00 | $55.00 | $1.10 | $13.75 |
| au.anthropic.claude-fable-5 | $11.00 | $55.00 | $1.10 | $13.75 |
| azure_ai/claude-fable-5 | $10.00 | $50.00 | $1.00 | $12.50 |
| bedrock/claude_platform/claude-fable-5 | $10.00 | $50.00 | $1.00 | $12.50 |
| deepinfra/anthropic/claude-fable-5 | $10.00 | $50.00 | — | — |
| eu.anthropic.claude-fable-5 | $11.00 | $55.00 | $1.10 | $13.75 |
| github_copilot/claude-fable-5 | $10.00 | $50.00 | $1.00 | $12.50 |
| global.anthropic.claude-fable-5 | $10.00 | $50.00 | $1.00 | $12.50 |
| openrouter/anthropic/claude-fable-5 | $10.00 | $50.00 | $1.00 | $12.50 |
| perplexity/anthropic/claude-fable-5 | $10.00 | $50.00 | $1.00 | — |
| us.anthropic.claude-fable-5 | $11.00 | $55.00 | $1.10 | $13.75 |
| vertex_ai/claude-fable-5 | $10.00 | $50.00 | $1.00 | $12.50 |
Price history
No change to the listed rates since this log began on 2026-10-04.
Price a call with the free API
No key, no account. It uses this same table, and with "usage_shape": "openai" it takes the cached tokens out of prompt_tokens first, so they aren't billed twice.
curl -s https://api.aight.studio/api/cost \
-H 'content-type: application/json' \
-d '{"model": "claude-fable-5", "input_tokens": 20000, "output_tokens": 1500, "cache_read_tokens": 12000}'
Returns cost_usd, a breakdown per token type, the rates per 1M, and when the table last changed. Rates only: GET https://api.aight.studio/api/pricing?models=a,b. Rate-limited per client; an unknown model is a 404, never $0. Full API docs.
pip install aight && aight-collect --report prices your Claude Code, Codex or Gemini CLI history locally with no account.