Skip to main content
POST
/
question
/
stream
Ask a question (SSE stream)
curl --request POST \
  --url http://localhost:{port}/question/stream \
  --header 'Content-Type: application/json' \
  --data '
{
  "question": "<string>",
  "resources": [
    "<string>"
  ],
  "quiet": true
}
'
"<string>"

Documentation Index

Fetch the complete documentation index at: https://thebettercontextapp-davis-npm-resource-on-web.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

Streams server-sent events for the query lifecycle.

​
Events

SSE format: 
event: <type>
data: <json>
Event types:
  • meta
  • reasoning.delta
  • text.delta
  • tool.updated
  • done
  • error

​
done

The final event is done. It always includes text, reasoning, and tools, and may include optional usage and metrics: 
{
	"type": "done",
	"text": "final answer",
	"reasoning": "full reasoning",
	"tools": [],
	"usage": {
		"inputTokens": 1234,
		"outputTokens": 456,
		"reasoningTokens": 120,
		"totalTokens": 1690
	},
	"metrics": {
		"timing": { "totalMs": 5321, "genMs": 2710 },
		"throughput": {
			"outputTokensPerSecond": 168.3,
			"totalTokensPerSecond": 623.6
		},
		"pricing": {
			"source": "models.dev",
			"modelKey": "openai/gpt-4o-mini",
			"ratesUsdPerMTokens": { "input": 0.14, "output": 0.54 },
			"costUsd": { "input": 0.000173, "output": 0.000246, "total": 0.000419 }
		}
	}
}
Notes:
  • Pricing is best-effort and may be omitted.
  • Pricing rates are USD per 1M tokens from https://models.dev/api.json.

Body

application/json
​
question
string
required
​
resources
string[]
​
quiet
boolean

Response

Server-sent events stream. Event types: meta, reasoning.delta, text.delta, tool.updated, done, error. The final done event may include optional usage and metrics fields.

The response is of type string.