stream_usage_inject
Injects stream_options.include_usage = true into streaming OpenAI chat-completions requests so the upstream response contains token usage.
Versions marked “overview” do not contain this page. Selecting one opens that version’s documentation overview.
On this page
Injects stream_options.include_usage = true into streaming OpenAI chat-completions requests so the upstream response contains token usage.
Configuration
| Field | Type | Required | Description |
|---|---|---|---|
max_body_bytes | integer | no | Maximum request body bytes for StreamBuffer mode. The cap applies to every request traversing the chain, not only streaming chat completions. |
Example
filter: stream_usage_inject