Claude Fable 5.2 in Claude Code: limits and cost

Claude Code runs on the same plan limits as Claude chat, so the table above applies. On Max, Ultra and Team premium seats, Fable 5.2 is included up to 50% of the weekly limit. On Pro and Team standard, it is included only during the launch week through Nov 16, then billed as usage credits. Medium effort is the default in Claude apps and Claude Code, per Anthropic.

What Fable 5.2 costs on an API key

If ANTHROPIC_API_KEY is set, Claude Code bills that key instead of your plan, per Anthropic's Claude Code plan page. Here is what that looks like at list price, before caching. Real coding sessions reuse a lot of context, and Fable 5.2 cache reads cost $0.20 per million tokens, so cached work costs much less.

Fast mode in Claude Code

Fable 5.2 fast mode generates tokens up to 2.5 times faster and is available in Claude Code, per Anthropic. On the API it costs $16 input and $80 output per million tokens, double the standard price. Anthropic has not said in its launch materials how fast mode counts against plan limits.

Does Fable 5.2 burn limits slower than Fable 5.1?

Anthropic says that at Medium effort Fable 5.2 can finish challenging tasks with fewer tokens than Fable 5.1, and that at High effort it scored about level with Opus 5.5 at Max effort on FrontierCode 2.0 for roughly half the cost per task. That is Anthropic's benchmark claim, not a measured plan allowance.

Verdict

Opus 5.5 stays the daily driver in Claude Code: it costs half as much per token and Anthropic recommends starting there. Switch to Fable 5.2 for the hard jobs, like big migrations or long agent runs, where Anthropic reports it leads every rival on FrontierCode and FrontierSWE. On a plan, Max is the cheapest way to keep Fable in Claude Code after Nov 16.

Full launch coverage: Claude Fable 5.2 and Mythos 5.2: prices, limits and what changed.