promptlayer

library1.4.6pypypi✓ verified 86d ago

PromptLayer is a platform for prompt engineering and tracking LLM requests. It provides middleware to log, debug, and analyze prompts for OpenAI, Anthropic, and other providers. Current version 1.4.3, actively maintained with regular releases.

llm-agents ai-ml

pip install promptlayer

package ↗homepage ↗

INSTALL

IMPORT

SIG · PROMPTLAYER

promptlayer

llm-agentspythonv1.4.6

Install

7.2s avg

Import

1405ms

Disk

48MB

Pass rate

10/ 10

Env Coverage10 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v1.4.6 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

py 3.10–3.95 runs

installs and imports cleanly · install 0.0s · import 1.624s · 46.2MB

glibc

py 3.10–3.95 runs

installs and imports cleanly · install 7.2s · import 1.186s · 49MB

48MB installed

● package 48MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

promptlayer

✓ import promptlayer

The main module is imported directly; no submodule needed.

PromptLayerOpenAI

✓ from promptlayer.openai import PromptLayerOpenAI

✗ from promptlayer import PromptLayerOpenAI

PromptLayerOpenAI is a class in the openai submodule, not top-level.

Initializes PromptLayer, sets API key, and uses the PromptLayerOpenAI client to track an OpenAI call.

import promptlayer # Initialize PromptLayer with your API key promptlayer.api_key = os.environ.get('PROMPTLAYER_API_KEY', '') # Wrap OpenAI client for tracking from promptlayer.openai import PromptLayerOpenAI import openai # Option 1: Use PromptLayerOpenAI client directly client = PromptLayerOpenAI(api_key=os.environ.get('OPENAI_API_KEY', ''), pl_tags=['test']) response = client.chat.completions.create( model='gpt-3.5-turbo', messages=[{'role': 'user', 'content': 'Hello!'}] ) print(response.choices[0].message.content) # Option 2: Patch the default OpenAI module (deprecated in v1.0) # promptlayer.openai.patch() # response = openai.ChatCompletion.create(...)

promptlayer --version

Debug

Known issues

breakingIn version 1.0, the default import changed. Previously `import promptlayer` would patch modules automatically; now you must explicitly use the wrapper classes (e.g., PromptLayerOpenAI) or call `promptlayer.openai.patch()`.

fix

Use `from promptlayer.openai import PromptLayerOpenAI` and instantiate it, or call `promptlayer.openai.patch()` after import.

affects: >=1.0.0

deprecatedThe method `promptlayer.openai.patch()` is deprecated. Direct class instantiation is preferred.

fix

Use `PromptLayerOpenAI` wrapper class instead of patching.

affects: >=1.0.0

gotchaThe `api_key` must be set for PromptLayer to log requests. If not set, requests will fail silently or raise an error depending on the version.

fix

Set `promptlayer.api_key = 'your_api_key'` or export `PROMPTLAYER_API_KEY` environment variable.

affects: all

Errors

Common errors & fixes

ModuleNotFoundError: No module named 'promptlayer'

PromptLayer not installed or installed in wrong environment.

fix

Run `pip install promptlayer` in your current Python environment.

AttributeError: module 'promptlayer' has no attribute 'openai'

Outdated version of promptlayer that does not have the openai submodule (pre-1.0).

fix

Upgrade promptlayer: `pip install --upgrade promptlayer`

InvalidRequestError: API key not provided. Set your PromptLayer API key via promptlayer.api_key or environment variable.

PromptLayer API key missing.

fix

Set `promptlayer.api_key = 'your_key'` or export `PROMPTLAYER_API_KEY` environment variable.

Upgrade

Version history

1.4.6latest on PyPI · released Jun 1, 2026

Audit

Dependencies

No dependency data recorded yet.

Agent activity

20 hits · last 30 days

node

OpenAI (training)

Resources

packagehttps://pypi.org/project/promptlayer/ ↗

homepagehttps://promptlayer.com ↗