Anthropic / anthropic/claude-fable-5.1

Claude Fable 5.1 - access through LLMTR

Claude Fable 5.1 is Anthropic's most capable widely released model for long-horizon agent tasks, large codebases, complex knowledge work, and vision-heavy production workflows. It offers a 1M context window, 128K max output, always-on adaptive thinking, vision and document input, tool calling, and prompt cache support. Effort is configurable from low through max: keep it low for short tasks and raise it for demanding agentic work. Prompt cache reads cost a quarter of what they do on Fable 5, so agent loops that re-read the same context get noticeably cheaper. It is subject to Anthropic's 30-day retention requirement.

Technical specifications

Canonical IDanthropic/claude-fable-5.1
ProviderAnthropic
Context window1,000,000 tokens
OperationsCHAT_COMPLETIONS
Modalitiestext, image

Pricing

An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
CHAT_COMPLETIONSINPUT_TEXTPER_1M_TOKENS$10.00
CHAT_COMPLETIONSCACHE_READPER_1M_TOKENS$0.250000
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$50.00
CHAT_COMPLETIONSCACHE_WRITEPER_1M_TOKENS$12.50
CHAT_COMPLETIONSCACHE_WRITEPER_1M_TOKENS$20.00

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{"model":"anthropic/claude-fable-5.1","messages":[{"role":"user","content":"Hello"}]}'

Related models