Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.openpipe.ai/llms.txt

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

If you’d like to make chat completion requests to Anthropic models without modifying your prompt schema, you can proxy OpenAI-compatible requests through OpenPipe, and we’ll handle the translation for you. To proxy requests to Anthropic models, first add your Anthropic API Key to your project settings. Then, adjust the model parameter of your requests to be the name of the model you wish to query, prepended with the string anthropic:. For example, to make a request to claude-3-5-sonnet-20241022, use the following code: 
from openpipe import OpenAI

# Find the config values in "Installing the SDK"
client = OpenAI()

completion = client.chat.completions.create(
    model="anthropic:claude-3-5-sonnet-20241022",
    messages=[{"role": "system", "content": "count to 10"}],
    metadata={"prompt_id": "counting", "any_key": "any_value"},
)
For your reference, here is a list of the most commonly used Anthropic models formatted for the OpenPipe proxy:
  • anthropic:claude-3-7-sonnet-20250219
  • anthropic:claude-3-5-sonnet-20241022
  • anthropic:claude-3-opus-20240229
  • anthropic:claude-3-sonnet-20240229
  • anthropic:claude-3-haiku-20240307
Additionally, you can always stay on the latest version of the model by using an abbreviated model name:
  • anthropic:claude-3-7-sonnet
  • anthropic:claude-3-5-sonnet
  • anthropic:claude-3-opus
  • anthropic:claude-3-sonnet
  • anthropic:claude-3-haiku
If you’d like to make requests directly to Anthropic models, you can do that externally using the Anthropic SDK, and report your logs using the asynchronous reporting API.