Files

10 lines
402 B
Plaintext

# Streaming asks for usage; a server that omits it is counted as unpriced
stream request body asks for usage (stream_options.include_usage): true
request fragment: "stream":true
two calls to a server that omits the usage block (/ask and /stream):
gen_ai.client.token.usage total, before 7 -> after 7
app.ai.unpriced{reason=no-usage} for ask : 1
app.ai.unpriced{reason=no-usage} for stream: 1