Back to model catalog

Compare models

Context, limits, capabilities, price and use cases side by side — up to 4 models at a time. The URL holds your selection, so you can share it.

Claude Fable 5.2Chat with this model
AttributeClaude Fable 5.2anthropic/claude-fable-5-2
Specs
Context window1M
Max output128K
Input modalitiesTextImage
Output modalitiesText
Capabilities
StreamingSupported
Tool callingSupported
Structured output (JSON)Supported
Image inputSupported
Thinking modeSupported
Price / 1M tokens
Input$ 8.00
Output$ 40.00
Cache read$ 0.20
Cache write$ 10.00
What it is good at
Best for
  • Agentic coding
  • Multistep research
  • Professional knowledge work
Published benchmarks
FrontierCode 2.0score
  • 49.1%effort xhigh · Claude Code(setup not fully disclosed)
FrontierSWE v2score
  • 69.9%effort max · Proximal(setup not fully disclosed)
Terminal-Bench 4.0pass_rate
  • 67.6%effort max · Claude Code(setup not fully disclosed)
AutomationBenchscore
  • 51.4%effort max(setup not fully disclosed)
SWE-Bench Proresolved_rate
  • 93%effort max(setup not fully disclosed)
OSWorld 2.1 (offline subset, partial score)score
  • 89.3%effort max(setup not fully disclosed)
AA-Briefcase v1.1score
  • 1785effort max(setup not fully disclosed)
Chartography (no tools)score
  • 73.4%effort max(setup not fully disclosed)
Humanity's Last Examaccuracy
  • 73.2%effort max(setup not fully disclosed)
Humanity's Last Exam (with tools)accuracy
  • 74.2%effort max(setup not fully disclosed)