OpenAI compatibility

codexkey has an OpenAI-compatible /v1/chat/completions endpoint, so Claude models are reachable from the OpenAI SDK and any OpenAI-compatible client.

Endpoint

http

POST https://api.codexkey.online/v1/chat/completions

Authentication

Send the key in the standard Authorization: Bearer header:

http

Authorization: Bearer sk_cdx_YOUR_KEY

Request body

Parameter	Type	Required	Description
`model`	string	Yes	Model ID (e.g. claude-sonnet-5).
`messages`	array	Yes	Array of messages; each has a role ("system", "user" or "assistant") and content.
`temperature`	number	No	Sampling temperature, from 0 to 1.
`max_tokens`	integer	No	Maximum tokens to generate.
`stream`	boolean	No	Enable streaming via SSE.

Field mapping

codexkey converts between the OpenAI and Anthropic formats on its own:

OpenAI Field	Anthropic equivalent	Notes
`messages[role="system"]`	`system`	System messages are pulled out and sent as a separate system parameter.
`max_tokens`	`max_tokens`	Direct mapping.
`temperature`	`temperature`	Direct mapping.
`stop`	`stop_sequences`	Accepts string or array.
`choices[0].message`	`content`	The response text is wrapped in the OpenAI format.
`choices[0].finish_reason`	`stop_reason`	end_turn → stop, max_tokens → length.

cURL Example

bash

curl https://api.codexkey.online/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk_cdx_YOUR_KEY" \
  -d '{
    "model": "claude-sonnet-5",
    "max_tokens": 1024,
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ]
  }'

Python example (OpenAI SDK)

python

from openai import OpenAI

client = OpenAI(
    api_key="sk_cdx_YOUR_KEY",
    base_url="https://api.codexkey.online/v1",
)

response = client.chat.completions.create(
    model="claude-sonnet-5",
    max_tokens=1024,
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing in one paragraph."},
    ],
)

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

PreviousModels NextCursor IDE