# Inferrence Streaming Changed

## post by 101100 on May 13, 2025

I’ve noticed that in the last few days, the inference API streaming mode has changed in two ways:

- The streaming mode tends to send practically the entire response in one chunk instead of sending things as they are generated.
- The library I’m using (the Rust crate `async_openai`) is giving an error that the `[DONE]` token is not being received.

Was this intentional or should I open a support ticket?

82 views

### Related topics

| Topic | Replies | Views | Activity |
| --- | --- | --- | --- |
| [Did inference api change recently?](https://deeptalk.lambda.ai/t/did-inference-api-change-recently/4569) | [0](https://deeptalk.lambda.ai/t/did-inference-api-change-recently/4569/1) | 117 | [Mar 2025](https://deeptalk.lambda.ai/t/did-inference-api-change-recently/4569/1) |
| [Does Inference API support batch/asynchronous processing](https://deeptalk.lambda.ai/t/does-inference-api-support-batch-asynchronous-processing/4540) | [1](https://deeptalk.lambda.ai/t/does-inference-api-support-batch-asynchronous-processing/4540/1) | 137 | [Mar 2025](https://deeptalk.lambda.ai/t/does-inference-api-support-batch-asynchronous-processing/4540/2) |
| [I’m getting an HTTP code 524 response from the the inference API’s](https://deeptalk.lambda.ai/t/im-getting-an-http-code-524-response-from-the-the-inference-apis/4535) | [0](https://deeptalk.lambda.ai/t/im-getting-an-http-code-524-response-from-the-the-inference-apis/4535/1) | 91 | [Mar 2025](https://deeptalk.lambda.ai/t/im-getting-an-http-code-524-response-from-the-the-inference-apis/4535/1) |
| [Inference API Timeout](https://deeptalk.lambda.ai/t/inference-api-timeout/4643) | [2](https://deeptalk.lambda.ai/t/inference-api-timeout/4643/1) | 156 | [Jun 2025](https://deeptalk.lambda.ai/t/inference-api-timeout/4643/3) |
| [Tool calling in Lambda Inference API](https://deeptalk.lambda.ai/t/tool-calling-in-lambda-inference-api/4448) | [6](https://deeptalk.lambda.ai/t/tool-calling-in-lambda-inference-api/4448/1) | 361 | [Jun 2025](https://deeptalk.lambda.ai/t/tool-calling-in-lambda-inference-api/4448/7) |