BraintrustExporter

Sends Tracing data to Braintrust for eval and observability.

Constructor

new BraintrustExporter(config: BraintrustExporterConfig)

BraintrustExporterConfig

interface BraintrustExporterConfig extends BaseExporterConfig {
  apiKey?: string
  endpoint?: string
  projectName?: string
  braintrustLogger?: Logger<true>
  currentSpan?: () => Span | undefined
  tuningParameters?: Record<string, any>
}

Extends BaseExporterConfig, which includes:

• logger?: IMastraLogger - Logger instance
• logLevel?: LogLevel | 'debug' | 'info' | 'warn' | 'error' - Log level (default: INFO)

Methods

exportTracingEvent

async exportTracingEvent(event: TracingEvent): Promise<void>

Exports a tracing event to Braintrust.

export

async export(spans: ReadOnlySpan[]): Promise<void>

Batch exports spans to Braintrust.

flush

async flush(): Promise<void>

Force flushes any buffered spans to Braintrust without shutting down the exporter. Useful in serverless environments where you need to ensure spans are exported before the runtime terminates.

shutdown

async shutdown(): Promise<void>

Flushes pending data and shuts down the client.

Usage

Zero-Config (using environment variables)

import { BraintrustExporter } from '@mastra/braintrust'

// Reads from BRAINTRUST_API_KEY, BRAINTRUST_ENDPOINT
const exporter = new BraintrustExporter()

Explicit Configuration

import { BraintrustExporter } from '@mastra/braintrust'

const exporter = new BraintrustExporter({
  apiKey: process.env.BRAINTRUST_API_KEY,
  projectName: 'my-ai-project',
})

Span type mapping

Span Type	Braintrust Type
MODEL_GENERATION	llm
MODEL_CHUNK	llm
TOOL_CALL	tool
MCP_TOOL_CALL	tool
PROVIDER_TOOL_CALL	tool
WORKFLOW_CONDITIONAL_EVAL	function
WORKFLOW_WAIT_EVENT	function
All others	task

Cost tracking

Braintrust uses a span's metrics.estimated_cost as its cost when the field is set, and estimates the cost from token metrics and its own model prices when it isn't. The exporter sets metrics.estimated_cost on a model generation span only when the generation's cost metadata meets every condition:

• costContext.costMetadata.source is 'provider_reported', meaning the model provider returned the cost, as OpenRouter and Vercel AI Gateway do.
• costContext.costUnit is 'USD'.
• costContext.estimatedCost is a finite number greater than 0.

Mastra's own cost estimates aren't exported, so Braintrust prices those spans with its model prices. A reported cost of 0 is skipped as well. Vercel AI Gateway reports 0 for bring-your-own-key requests, which your model provider still bills, and Braintrust's estimate is closer to that charge. The span metadata keeps the full costContext in every case.