Claude Fable 5.2

Claude Fable 5.2 is a chat model published by Anthropic, the company behind the Claude line of assistants. It is listed in our catalog as a conversational text model, meaning it is designed to take a prompt or multi-turn dialogue and return generated text. Beyond the creator and model type, our database does not carry confirmed details on this model's context window, modality support, or parameter scale, so this page focuses on what has been measured directly rather than on specifications we cannot verify. On the performance side, independent measurements from Artificial Analysis put Claude Fable 5.2 at roughly 94.67 output tokens per second, which places it in a mid-to-upper range for generation speed among chat models that report this metric. The measured time to first token is unusually long at approximately 253,380 milliseconds (about four minutes), a figure that typically indicates extended internal processing before the first visible token is emitted rather than a simple network delay. Together these numbers describe a model that, once it begins responding, streams at a reasonable rate, but that can take a substantial amount of wall-clock time before output begins. In practice, that latency profile shapes where Claude Fable 5.2 fits. It is a poor match for interactive chat interfaces where a user is waiting on screen, and a better match for asynchronous or batch workloads where a job can be submitted and collected later. Readers comparing it against other Anthropic Claude models or third-party chat models should weigh the throughput figure against the first-token delay, and should consult the pricing table on this page to see how the available providers price it.