claude-fable-5

claude-fable-5

Claude Fable 5 is our most intelligent Fable model and the best generally available model for coding and agents, with deeper reasoning for enterprise workflows.
Anthropic
Version: 1
These models constitute the vast majority of the Azure AI Foundry Models and are provided by trusted third-party organizations, partners, research labs, and community contributors. These models offer specialized and diverse AI capabilities, covering a wide array of scenarios, industries, and innovations. An example of models from Partners and community are the family of large language models developed by Anthropic. Anthropic includes Claude family of state-of-the-art large language models that support text and image input, text output, multilingual capabilities, and vision. See Anthropic's privacy policy to know more about privacy. Learn how to deploy Anthropic models . Characteristics of Models from Partners and Community:
  • Developed and supported by external partners and community contributors.
  • Diverse range of specialized models catering to niche or broad use cases.
  • Typically validated by providers themselves, with integration guidelines provided by Azure.
  • Community-driven innovation and rapid availability of cutting-edge models.
  • Standard Azure AI integration, with support and maintenance managed by the respective providers.
Models from Partners and Community are deployable as Managed Compute or serverless API deployment options. The model provider selects how the models are deployable.

About this model

Claude Fable 5 is our next generation of intelligence for the hardest knowledge work and coding problems. It works independently for longer than any prior generally available Claude model: run it in an agent harness and it can work for days at a time, planning across stages, delegating to sub-agents, and checking its own work.

Key model capabilities

  • Long-horizon autonomy: Claude Fable 5 works independently for longer than any prior generally available Claude model — planning across stages, tracking dependencies, and routing around blockers on tasks where previous models needed frequent check-ins.
  • Self-verification: Claude Fable 5 checks its own work: it writes its own tests for code and uses vision to verify outputs against the original design or goal, so teams can review finished work rather than supervise every step.
  • Sub-agent orchestration: In an agent harness like Claude Code Claude Fable 5 can sustain multi-day projects, delegating work to sub-agents and carrying context across stages.

Quick facts

Model providerAnthropic
TypeMessages
LifecycleGenerally available (GA)
Input typetext, image, code
Output typetext, image, code
Context window1000k
Token limits128k output
PricingView pricing

Quick Start

Sign in to get startedView DocumentationAzure Support