OpenAI SDK

The official OpenAI SDKs work unchanged. Set the base URL to https://api.abliteratedllm.dev/v1 and use your API key. Both chat completions and the stateless Responses API are available.

Placeholders: $API_BASE is https://api.abliteratedllm.dev/v1, $API_ORIGIN is https://api.abliteratedllm.dev, and $YOUR_KEY is your API key.

Both SDKs also read the OPENAI_BASE_URL and OPENAI_API_KEY environment variables, so existing code can switch without edits:

export OPENAI_BASE_URL="$API_BASE"
export OPENAI_API_KEY="$YOUR_KEY"

Python

pip install openai

Chat completions, streamed:

from openai import OpenAI

client = OpenAI(base_url="$API_BASE", api_key="$YOUR_KEY")

stream = client.chat.completions.create(
    model="glm-5.3-flash-abliterated",
    messages=[
        {"role": "system", "content": "You are a witty fantasy narrator."},
        {"role": "user", "content": "Describe a tavern brawl in four sentences."},
    ],
    reasoning_effort="low",
    max_tokens=1024,
    stream=True,
)
for chunk in stream:
    # Usage arrives in a final chunk whose choices list is empty.
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="", flush=True)
    if chunk.usage:
        print(f"\n\n{chunk.usage.prompt_tokens} in, {chunk.usage.completion_tokens} out")

Responses API (stateless, so send the whole conversation each time):

response = client.responses.create(
    model="glm-5.3-flash-abliterated",
    instructions="Answer in one sentence.",
    input="What is the boiling point of water at sea level in Fahrenheit?",
    reasoning={"effort": "low"},
)
print(response.output_text)

JavaScript and TypeScript

npm install openai

Chat completions, streamed:

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "$API_BASE", apiKey: "$YOUR_KEY" });

const stream = await client.chat.completions.create({
  model: "glm-5.3-flash-abliterated",
  messages: [
    { role: "system", content: "You are a witty fantasy narrator." },
    { role: "user", content: "Describe a tavern brawl in four sentences." },
  ],
  reasoning_effort: "low",
  max_tokens: 1024,
  stream: true,
});
for await (const chunk of stream) {
  // Usage arrives in a final chunk whose choices array is empty.
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
  if (chunk.usage) console.log(`\n\n${chunk.usage.prompt_tokens} in, ${chunk.usage.completion_tokens} out`);
}

Responses API:

const response = await client.responses.create({
  model: "glm-5.3-flash-abliterated",
  instructions: "Answer in one sentence.",
  input: "What is the boiling point of water at sea level in Fahrenheit?",
  reasoning: { effort: "low" },
});
console.log(response.output_text);

Good to know

• Errors use the OpenAI shape, so the SDKs raise their usual exceptions (RateLimitError, AuthenticationError and so on). Each error carries one of our error codes in code.
• Retries. By default the SDKs retry 429 and 5xx responses a few times and honor the Retry-After header we send with capacity_exhausted.
• Responses are stateless: store is always false, and previous_response_id returns 400 stateless_only. See POST /v1/responses.
• Text only. Image, audio and file inputs fail with 400 unsupported_content.

Verified against OpenAI SDK docs on 2026-11-03: openai-python (base_url, OPENAI_BASE_URL) and openai-node (baseURL, OPENAI_BASE_URL).