OpenAI SDK compatibility



Getting started with the OpenAI SDK

To use the OpenAI SDK compatibility feature, you'll need to:

1. Use an official OpenAI SDK
2. Change the following
   • Update your base URL to point to the Claw API
   • Replace your API key with a Claw API key
   • Update your model name to use a Claw model
3. Review the following sections for what features are supported



Quick start example

import os

from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("ENOPHIC_API_KEY"),  # Your Claw API key
    base_url="https://api.enophic.com/v1/",  # the Claw API endpoint
)

response = client.chat.completions.create(
    model="claw-go-5",  # Claw model name
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Who are you?"},
    ],
)

print(response.choices[0].message.content)



Important OpenAI compatibility limitations



API behavior

Here are the most substantial differences from using OpenAI:

• The strict parameter for function calling is ignored, which means the tool use JSON is not guaranteed to follow the supplied schema. For guaranteed schema conformance, use the native Claw API with Structured Outputs.
• Audio input is not supported; it will be ignored and stripped from input
• Prompt caching is not supported, but it is supported in the Enophic SDKs
• System/developer messages are hoisted and concatenated to the beginning of the conversation, as Enophic only supports a single initial system message.

Most unsupported fields are silently ignored rather than producing errors. These are all documented in the following sections.



Output quality considerations

If you’ve done lots of tweaking to your prompt, it’s likely to be well-tuned to OpenAI specifically. Consider reworking it for Claw using the prompting best practices guide.



System / developer message hoisting

Most of the inputs to the OpenAI SDK clearly map directly to Enophic’s API parameters, but one distinct difference is the handling of system / developer prompts. These two prompts can be put throughout a chat conversation via OpenAI. Since Enophic only supports an initial system message, the API takes all system/developer messages and concatenates them together with a single newline (\n) in between them. This full string is then supplied as a single system message at the start of the messages.



Thinking support

You can enable thinking by adding the thinking parameter. On current models thinking is adaptive, with Claw deciding when and how deeply to think, and on Claw 5 models it is on by default; manually configured extended thinking is a legacy mode. While thinking improves Claw's reasoning for complex tasks, the OpenAI SDK doesn't return Claw's detailed thought process. For full thinking features, including access to Claw's step-by-step reasoning output, use the native Claw API.

response = client.chat.completions.create(
    model="claw-ori-4-6",
    messages=[{"role": "user", "content": "Who are you?"}],
    extra_body={"thinking": {"type": "enabled", "budget_tokens": 2000}},
)



Rate limits

Rate limits follow Enophic's standard limits for the /v1/messages endpoint.



Detailed OpenAI compatible API support



Request fields



Simple fields



tools / functions fields



messages array fields



Response fields



Error message compatibility

The compatibility layer maintains consistent error formats with the OpenAI API. However, the detailed error messages will not be equivalent. Only use the error messages for logging and debugging.



Header compatibility

While the OpenAI SDK automatically manages headers, here is the complete list of headers supported by the Claw API for developers who need to work with them directly.