Anthropic: Claude Fable 5

Claude Fable 5 is a text model from Anthropic, listed on api14 under the model id anthropic/claude-fable-5. It is described as a Mythos-class model built for autonomous knowledge work and coding, and its provider release date is 2026-06-09. If you are choosing between providers on api14, this is the Anthropic entry in the Claude Fable line, and it sits in the text category rather than in a specialised image, audio or embedding category.

The model accepts text, image and file inputs and returns text output. Its context window is 1,000,000 tokens, which is large enough to hold entire codebases, long document sets or extended conversation histories in a single request, and its maximum output is 128,000 tokens, so long generated answers, reports or code files can be produced in one call. Reasoning support is part of the model's design, and the request parameters include reasoning, reasoning_effort, include_reasoning and verbosity, which let you control how much internal reasoning is exposed or requested and how verbose the response is.

Those capabilities point to a few practical patterns. Long-context work such as reviewing a full repository, summarising or extracting structured data from large document collections, and answering questions across many files at once fits the 1,000,000 token window. Because image and file inputs are supported alongside text, you can mix screenshots, diagrams or documents into the same prompt as written instructions. Tool use and structured outputs make it a reasonable fit for agent-style workflows and for pipelines that need machine-readable responses rather than free prose, and the reasoning controls suit tasks where you want the model to work through a problem before answering.

You call it through api14's OpenAI-compatible API using the model id anthropic/claude-fable-5, so existing OpenAI SDK clients work with a base URL change. The supported request parameters are include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, stop, structured_outputs, tool_choice, tools and verbosity. Use max_tokens or max_completion_tokens to cap output, response_format or structured_outputs when you need a defined shape, and tools with tool_choice when the model should call functions. Note that output is text only, so if you need generated images or audio, a different model is the right choice.