[▲ Vercel Community](/) · [Categories](/categories) · [Latest](/latest) · [Top](/top) · [Live](/live)

[AI SDK](/c/ai-sdk/62)

# Openrouter support in AI sdk v5

450 views · 2 likes · 6 posts


sunney (@sunney) · 2025-08-06

how come openrouter the most crucial provider is not supported in AI sdk v5? am i missing something?

![image|690x102](upload://rBcWh3k8xjYxvtolHzU7plRb5iL.png)


Amy Egan (@amyegan) · 2025-08-06

I believe the [beta version](https://www.npmjs.com/package/@openrouter/ai-sdk-provider/v/beta) is currently compatible


Arkmaster123 (@arkmaster123) · 2025-08-20

hey has this been resolved? thanks


Amy Egan (@amyegan) · 2025-08-20 · ♥ 2

Looks like it's out of beta, so it should work now. But please let me know if you're still having trouble with it!


wowsers (@jadams777) · 2025-08-27

I can’t get streamText() working in an Expo SDK 53 iOS app with OpenRouter and @openrouter/ai-sdk-provider. generateText() works fine, but it’s too slow.  Any suggestions?


Faresmakki (@faresmakki) · 2025-10-03

 @sunney @amyegan @arkmaster123 @jadams777  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 thinks this mean that this the 5min cache not the 1hour cache