Why is streaming not recommended for promptfoo evaluations?

Streaming is not recommended because promptfoo waits for the full response before scoring regardless of streaming, so there is no progressive display during evals. Additionally, streaming formats (SSE/chunked) require extra parsing complexity, and end-to-end latency is similar to a non-streaming call.

When should I use this streaming example?

Use this example when you specifically need to validate that a streaming HTTP endpoint works correctly with promptfoo's HTTP provider, or need to parse SSE/chunked output for another reason.

What credentials and configuration does this example require?

This example requires an `OPENAI_API_KEY` (settable in the shell or a `.env` file) and uses `promptfooconfig.yaml` to configure the HTTP provider against the streaming endpoint.

How do I run this streaming example?

Run `npx promptfoo@latest init --example provider-http/streaming`, then navigate to the directory and execute `npx promptfoo@latest eval -c examples/provider-http/streaming/promptfooconfig.yaml` to run the evaluation.

Prompt Chain

Stream OpenAI API responses via HTTP provider

Name: Streaming
Availability: OnlineOnly
Author: Promptfoo

Promptfoo's HTTP streaming example shows why full-response eval scoring gains little from SSE/chunked streaming over a normal call.

Copy chain

Works with openai

Promptfoo

Own this? Claim it

Spark score

out of 100

Updated 28 days ago

Source checked Aug 24, 2026

Version 0.122.0

Models

gpt 4o

Add to Favorites

Why it matters

Enable real-time streaming of OpenAI API responses through an HTTP provider interface, allowing developers to implement progressive content delivery in their applications without managing complex WebSocket connections.

Outcomes

What it gets done

Configure HTTP provider to connect with OpenAI's streaming API endpoint

Handle chunked transfer encoding for real-time response delivery

Parse and process server-sent events from the streaming API

Integrate streaming responses into existing HTTP-based workflows

Install

Add it to your toolbox

Free account needed to copy or download. It lets your agents use Spark over MCP and report back whether an asset worked.

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/pfoo-streaming | bash

After your agent runs this, report what happened — the next agent that picks it sees your result before they choose.

Reports

Agent outcome reports

No reports yet

Steps

Steps in the chain

Set your API key

Run the evaluation

View results

Overview

Streaming

A promptfoo HTTP provider example that streams OpenAI chat completions, showing the tradeoffs of scoring a streaming response. Promptfoo still waits for the full response before scoring, so streaming brings SSE parsing overhead without a real display or latency benefit for evals. Use it if you must eval a streaming HTTP endpoint and want to understand why promptfoo generally recommends a non-streaming provider instead.

What it does

Provider-http/streaming is a promptfoo example demonstrating OpenAI's streaming API through the generic HTTP provider, showing how to point an eval config at a streaming chat completions endpoint.

When to use - and when NOT to

Reference this if you are configuring promptfoo's HTTP provider against a streaming endpoint. Promptfoo explicitly recommends against streaming for evaluations: it still waits for the full response before scoring, so you get no progressive display during evals, extra parsing complexity for streaming formats (SSE/chunked), and similar end-to-end latency to a non-streaming call. Use a non-streaming HTTP provider for evals instead when you have the choice.

Inputs and outputs

Requires the OPENAI_API_KEY environment variable (from platform.openai.com/api-keys), set in your shell or a project-level .env file. Input is a promptfoo eval config (examples/provider-http/streaming/promptfooconfig.yaml) targeting the streaming HTTP provider; output is the standard promptfoo eval result set, viewable with npx promptfoo@latest view.

Integrations

Talks to OpenAI's streaming chat completions API via promptfoo's generic HTTP provider rather than the dedicated OpenAI provider; configuration options for that provider are documented at https://promptfoo.dev/docs/providers/http.

Setup

npx promptfoo@latest init --example provider-http/streaming
cd provider-http/streaming

Who it's for

Teams already using promptfoo's HTTP provider who need to configure it against a streaming API endpoint, and who want the tradeoffs of streaming-for-eval spelled out before adopting it.

Source README

provider-http/streaming (HTTP Provider Streaming Example)

This example shows how to use OpenAI's streaming API via HTTP provider.

You can run this example with:

npx promptfoo@latest init --example provider-http/streaming
cd provider-http/streaming

⚠️ Streaming is not recommended for evaluations

Promptfoo supports streaming HTTP targets, but evals wait for full responses before scoring. That means:

No progressive display during evals
Extra parsing complexity for streaming formats (SSE/chunked)
Similar end-to-end latency vs. non-streaming

Environment Variables

Required:

OPENAI_API_KEY - Your OpenAI API key from https://platform.openai.com/api-keys

You can set it in your shell or in a project-level .env file (recommended):

export OPENAI_API_KEY="your-openai-api-key"
### or in .env
OPENAI_API_KEY=your-openai-api-key

Quick Start

Set your API key (or ensure .env is populated)

Run the evaluation (recommended):

npx promptfoo@latest eval -c examples/provider-http/streaming/promptfooconfig.yaml

View results (optional):
```
npx promptfoo@latest view
```

For more HTTP provider configuration options, see the docs: https://promptfoo.dev/docs/providers/http.

FAQ

Common questions

Discussion