Fable 5.1 lands on OpenRouter with prompt cache reads cut 75%
- Source
- x.com
- Date
Claude Fable 5.1 from @AnthropicAI is live on OpenRouter. A direct upgrade for Fable 5 workloads, with the biggest gains in agentic coding, long-running workflows, visual code generation, finance, and analysis. Try it: https://t.co/a07gfACbQe
On pricing: Fable 5.1 keeps Fable 5 pricing at $10/M input tokens and $50/M output tokens. Prompt cache reads drop to $0.25/M tokens, 75% below the old cache-read rate. Read more: https://t.co/EZjBphBEIS
Context
The main price change when OpenRouter added Anthropic's Claude Fable 5.1 concerned reading previously cached input. The announced rate fell to $0.25 per million cached , 75% below the old cache-read rate, while ordinary input and output remained $10 and $50 per million tokens. Pricing announcement.
reuses a shared opening portion of earlier input, so this discount particularly helps requests that repeatedly supply the same material. The saving applies when those requests obtain cache hits; generating new output remains a separate charge. Caching documentation.
- token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
- prompt caching — Reusing the model's processed form of a repeated prompt prefix so subsequent calls skip re-reading it, cutting cost and latency substantially.
Checking sign-in…
Loading comments…