Release
Claude Fable 5.2 vs. Fable 5.1: Fewer refusals, with small savings on the login fix
The New Stack · By Jessica Wachtel ·
The Brief
- Anthropic says Claude Fable 5.2 has fewer refusals and lower token prices than Fable 5.1.
- Anthropic compared the two models on safeguard blocks, output speed, and API pricing.
- The New Stack's head-to-head coding tests showed the changes playing out very differently, with only small savings on a login fix.
Why it matters
Developers using Claude Fable models may see different refusal rates, response speed, and API costs after moving from 5.1 to 5.2, and coding results may not match the vendor's claims.
Who’s affected
- Developers using Claude Fable models via the API
- Teams using Claude for coding tasks
- Claude Fable 5.2
- Claude Fable 5.1
- #claude
- #anthropic
- #llm
- #coding
- #api-pricing
Anthropic’s Claude Fable 5.2 promises fewer refusals and lower token prices, but those changes played out very differently in our head-to-head coding comparisons. Anthropic compared Fable 5.2 with its predecessor, Fable 5.1 , on safeguard blocks, output speed, and API pricing…