# useChat/useCompletion stream output contains 0:... instead of text

## Issue

I am using custom client code to process a server response that is sent using `StreamingTextResponse`. I am using version `3.0.20` or newer of the AI SDK. When I send a query, the UI streams text such as `0: "Je"`, `0: " suis"`, `0: "des"...` instead of the text that I’m looking for.

## Background

The AI SDK has switched to the stream data protocol in version `3.0.20`. It sends different stream parts to support data, tool calls, etc. What you see is the raw stream data protocol response.

## Solution

You have several options:

1. Use the AI Core [`streamText`](/docs/reference/ai-sdk-core/stream-text) function to send a raw text stream:

   ```tsx
   export async function POST(req: Request) {
     const { prompt } = await req.json();

     const result = streamText({
       model: openai.completion('gpt-3.5-turbo-instruct'),
       maxOutputTokens: 2000,
       prompt,
     });

     return result.toTextStreamResponse();
   }
   ```

2. Pin the AI SDK version to `3.0.19` . This will keep the raw text stream.


## Navigation

- [Azure OpenAI Slow to Stream](/docs/troubleshooting/azure-stream-slow)
- [Server Actions in Client Components](/docs/troubleshooting/server-actions-in-client-components)
- [useChat/useCompletion stream output contains 0:... instead of text](/docs/troubleshooting/strange-stream-output)
- [Streamable UI Errors](/docs/troubleshooting/streamable-ui-errors)
- [Tool Invocation Missing Result Error](/docs/troubleshooting/tool-invocation-missing-result)
- [Streaming Not Working When Deployed](/docs/troubleshooting/streaming-not-working-when-deployed)
- [Streaming Not Working When Proxied](/docs/troubleshooting/streaming-not-working-when-proxied)
- [Getting Timeouts When Deploying on Vercel](/docs/troubleshooting/timeout-on-vercel)
- [Unclosed Streams](/docs/troubleshooting/unclosed-streams)
- [useChat Failed to Parse Stream](/docs/troubleshooting/use-chat-failed-to-parse-stream)
- [Server Action Plain Objects Error](/docs/troubleshooting/client-stream-error)
- [useChat No Response](/docs/troubleshooting/use-chat-tools-no-response)
- [Custom headers, body, and credentials not working with useChat](/docs/troubleshooting/use-chat-custom-request-options)
- [TypeScript performance issues with Zod and AI SDK 5](/docs/troubleshooting/typescript-performance-zod)
- [useChat "An error occurred"](/docs/troubleshooting/use-chat-an-error-occurred)
- [Repeated assistant messages in useChat](/docs/troubleshooting/repeated-assistant-messages)
- [onFinish not called when stream is aborted](/docs/troubleshooting/stream-abort-handling)
- [Tool calling with structured outputs](/docs/troubleshooting/tool-calling-with-structured-outputs)
- [Abort breaks resumable streams](/docs/troubleshooting/abort-breaks-resumable-streams)
- [streamText fails silently](/docs/troubleshooting/stream-text-not-working)
- [Streaming Status Shows But No Text Appears](/docs/troubleshooting/streaming-status-delay)
- [Stale body values with useChat](/docs/troubleshooting/use-chat-stale-body-data)
- [Type Error with onToolCall](/docs/troubleshooting/ontoolcall-type-narrowing)
- [Unsupported model version error](/docs/troubleshooting/unsupported-model-version)
- [Object generation failed with OpenAI](/docs/troubleshooting/no-object-generated-content-filter)
- [Missing Tool Results Error](/docs/troubleshooting/missing-tool-results-error)
- [Model is not assignable to type "LanguageModelV1"](/docs/troubleshooting/model-is-not-assignable-to-type)
- [TypeScript error "Cannot find namespace 'JSX'"](/docs/troubleshooting/typescript-cannot-find-namespace-jsx)
- [React error "Maximum update depth exceeded"](/docs/troubleshooting/react-maximum-update-depth-exceeded)
- [Jest: cannot find module '@ai-sdk/rsc'](/docs/troubleshooting/jest-cannot-find-module-ai-rsc)
- [High memory usage when processing many images](/docs/troubleshooting/high-memory-usage-with-images)


[Full Sitemap](/sitemap.md)