News Cache (2025-06-02)

:star: Community Highlights

Don’t forget to visit the Showcase to see what else everyone is building!

:books: Learn

:date: Events

▲ From Vercel

:information_source: ICYMI

3 Likes

Thank you for including us! We were thoroughly impressed by v0 :raising_hands:

2 Likes

Thanks for sharing your experience! Appreciate the feedback about the env var UI :smile:

1 Like

hi sorry for bothering,does anyone know if ai sdk support anthropic 1 hour prompt caching via openrouter , i tried what the docs saimessages: [

{

  role: 'system',

  content:

    'You are a podcast summary assistant. You are detail-oriented and critical about the content.',

},

{

  role: 'user',

  content: \[

    {

      type: 'text',

      text: 'Given the text body below:',

    },

    {

      type: 'text',

      text: \`<LARGE BODY OF TEXT>\`,

      providerOptions: {

        openrouter: {

          cacheControl: { type: 'ephemeral' ,ttl:"1h"},

        },

      },

    },

    {

      type: 'text',

      text: 'List the speakers?',

    },

  \],

},

],

it works, but the cache write cost 1.25×input not 2×input i think that this is the 5min cache not the 1hour cache

This topic was automatically closed after 179 days. New replies are no longer allowed.