What is SSE (Server-Sent Events) in the context of AI APIs?

When you call an AI API with stream: true, the server sends the response incrementally as a series of text lines in the format "data: {json}". Each line is one chunk. SSE allows the client to display text as it is generated rather than waiting for the full response.

How do I get SSE stream output to paste into this tool?

In your browser DevTools, open the Network tab, find the streaming API request, and copy the raw response body. Alternatively, if calling the API programmatically, log the raw response body before parsing. Then paste the raw "data: ..." lines into the tool.

What does the [DONE] line mean?

"data: [DONE]" is the standard SSE termination signal used by OpenAI-compatible APIs to indicate that the stream has ended. This tool automatically skips that line and does not count it as a chunk.

AI Streaming JSON Viewer

Parse and pretty-print SSE stream chunks from OpenAI and similar APIs.

SSE Stream Text

Paste SSE stream output above, or click Load sample to see an example

Related Tools

RPRAI JSON Repair ToolNEW

Fix broken LLM JSON: strip markdown fences, trailing commas, single quotes, and more.

FIXAI JSON FixerNEW

Extract and fix JSON from mixed LLM output — handles prose, markdown, and concatenation.

SCHAI JSON Schema BuilderNEW

Visually build JSON schemas for AI function calling and structured output.

VALAI Structured Output ValidatorNEW

Validate AI JSON output against a JSON Schema — check types, required fields, enums.

J2PAI JSON to PromptNEW

Generate a structured output prompt from a JSON example or schema.

Learn More

guide:structured output

FAQ

What is SSE (Server-Sent Events) in the context of AI APIs?: When you call an AI API with stream: true, the server sends the response incrementally as a series of text lines in the format "data: {json}". Each line is one chunk. SSE allows the client to display text as it is generated rather than waiting for the full response.
How do I get SSE stream output to paste into this tool?: In your browser DevTools, open the Network tab, find the streaming API request, and copy the raw response body. Alternatively, if calling the API programmatically, log the raw response body before parsing. Then paste the raw "data: ..." lines into the tool.
What does the [DONE] line mean?: "data: [DONE]" is the standard SSE termination signal used by OpenAI-compatible APIs to indicate that the stream has ended. This tool automatically skips that line and does not count it as a chunk.

Paste raw Server-Sent Events (SSE) stream text from OpenAI chat completions or similar APIs. The viewer parses each line starting with "data: ", skips [DONE] markers, attempts JSON.parse on each chunk, and displays a numbered list of pretty-printed JSON objects. Shows total chunk count. Useful for debugging streaming LLM responses and understanding the chunk structure.