The reason for buffering requests is so WAF can run on the request body.

    const response = await fetch(url, {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
        Authorization: `Bearer ${env.OPENAI_API_KEY}`,
      },
      body,
    })
      .then((res) => response.body)
      .then((body) => {
        const reader = body.getReader()

        // do stuff with reader
      })

    const response = await fetch(url, {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
        Authorization: `Bearer ${env.OPENAI_API_KEY}`,
      },
      body,
    })
      .then((res) => response.body)
      .then((body) => {
        const reader = body.getReader()

        // do stuff with reader
      })

const startTime = Date.now()

    const response = await fetch(url, {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
        Authorization: `Bearer ${env.OPENAI_API_KEY}`,
      },
      body,
    })

    if (!response.ok) {
      console.log(
        `Unexpected response from OpenAI API: ${response.status} ${response.statusText}`
      )
      return
    }

    if (!response.body) {
      console.log("No response body")
      return
    }
    const reader = response.body.getReader()

    // Get first byte
    let chunk = await reader.read()

    // Log first byte time
    const firstByteTime = Date.now() - startTime

    // Read the rest of the response
    while (!chunk.done) {
      chunk = await reader.read()
    }

const startTime = Date.now()

    const response = await fetch(url, {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
        Authorization: `Bearer ${env.OPENAI_API_KEY}`,
      },
      body,
    })

    if (!response.ok) {
      console.log(
        `Unexpected response from OpenAI API: ${response.status} ${response.statusText}`
      )
      return
    }

    if (!response.body) {
      console.log("No response body")
      return
    }
    const reader = response.body.getReader()

    // Get first byte
    let chunk = await reader.read()

    // Log first byte time
    const firstByteTime = Date.now() - startTime

    // Read the rest of the response
    while (!chunk.done) {
      chunk = await reader.read()
    }

 const totalTime = Date.now() - startTime

    console.log("Time to first byte: " + firstByteTime + "ms")
    console.log("Total response time: " + totalTime + "ms")

    // Log response time
    const client = new Client(env.DB_URL + "?sslmode=require")
    await client.connect()

    const text =
      "INSERT INTO response_times(model, date, ttfb, duration) VALUES($1, $2, $3, $4) RETURNING *"
    const values = [
      "gpt-4",
      new Date(event.scheduledTime),
      firstByteTime,
      totalTime,
    ]

    try {
      const res = await client.query(text, values)
      console.log(res.rows[0])
    } catch (err) {
      console.error(err)
    } finally {
      ctx.waitUntil(client.end())
    }

 const totalTime = Date.now() - startTime

    console.log("Time to first byte: " + firstByteTime + "ms")
    console.log("Total response time: " + totalTime + "ms")

    // Log response time
    const client = new Client(env.DB_URL + "?sslmode=require")
    await client.connect()

    const text =
      "INSERT INTO response_times(model, date, ttfb, duration) VALUES($1, $2, $3, $4) RETURNING *"
    const values = [
      "gpt-4",
      new Date(event.scheduledTime),
      firstByteTime,
      totalTime,
    ]

    try {
      const res = await client.query(text, values)
      console.log(res.rows[0])
    } catch (err) {
      console.error(err)
    } finally {
      ctx.waitUntil(client.end())
    }