OpenAI codex api: Quickstart with Python

Install the Official SDK

Use the official SDK to ensure compatibility with our openai proxy API. This approach works with any standard library that supports the OpenAI protocol.

• Install the package via your preferred package manager.
• Verify the installation by importing the library.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.openaicodexapi.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openaicodexapi.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Set Your Base URL and Key

Point your client to our openai gateway endpoint to access the uncensored AI model. Replace the default base URL with our specific endpoint.

• Set the API key in your environment variables.
• Configure the base URL to https://api.openaicodexapi.com/v1.

This setup ensures your requests route correctly to our servers without modifying your existing code structure.

Copycurl https://api.openaicodexapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Explain how prepaid billing works for this API."}]
  }'

Send Your First Request

Send a simple text completion to test the connection. Use the model ID uncensored for the request.

• Define the message content.
• Execute the request.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.openaicodexapi.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openaicodexapi.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

The response returns the generated text directly.

Enable Streaming and JSON Mode

Stream responses for lower latency or enforce JSON mode for structured data. Set stream=true for real-time token delivery.

• Use response_format for JSON output.
• Handle chunks in your code.

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Copycurl https://api.openaicodexapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Explain how prepaid billing works for this API."}]
  }'

Streaming helps you display partial results quickly.

Handle Tools and Function Calling

Define tools in your request to enable function calling. Specify the tool definitions and let the model decide when to use them.

• Define the function schema.
• Parse the tool calls in the response.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.openaicodexapi.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openaicodexapi.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

This feature allows integration with external systems.

Limits, Errors, and Context Window

Monitor your usage to avoid rate limits or errors. The context window supports 100,000 tokens total.

• Handle 401 errors for invalid keys.
• Handle 402 errors for insufficient credit.
• Handle 429 errors for rate limits.

Copycurl https://api.openaicodexapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Explain how prepaid billing works for this API."}]
  }'

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.openaicodexapi.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openaicodexapi.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)