OpenAI-compatible SDK

PulseNeko5/20/26Less than 1 minute

Bridge fully implements /v1/chat/completions, /v1/responses, /v1/embeddings, /v1/audio/*, /v1/images/*. Use the official SDK with a custom base_url.

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://bridge.pulseneko.com/v1",
    api_key="sk-your-key",
)

# Chat
resp = client.chat.completions.create(
    model="gpt-5.1",
    messages=[{"role": "user", "content": "Introduce PulseNeko Bridge in one sentence."}],
)
print(resp.choices[0].message.content)

Streaming

stream = client.chat.completions.create(
    model="gpt-5.1",
    messages=[{"role": "user", "content": "..."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Responses API (preferred for reasoning models)

resp = client.responses.create(
    model="gpt-5.3",
    input="Think about this: ...",
)
print(resp.output_text)

Embeddings

emb = client.embeddings.create(
    model="text-embedding-3-large",
    input=["first chunk", "second chunk"],
)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://bridge.pulseneko.com/v1",
  apiKey: process.env.PULSENEKO_KEY,
});

const resp = await client.chat.completions.create({
  model: "gpt-5.1",
  messages: [{ role: "user", content: "Hello" }],
});

console.log(resp.choices[0].message.content);

cURL

curl https://bridge.pulseneko.com/v1/chat/completions \
  -H "Authorization: Bearer sk-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.1",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Model names

Use the exact string from Model Catalog. Common:

gpt-5.1 / gpt-5.1-mini / gpt-5.1-nano
gpt-5.3 / gpt-5.3-codex
o4-mini
claude-opus-4-7 / claude-sonnet-4-6 / claude-haiku-4-5 — Bridge auto-translates when called via OpenAI path
gemini-3.1-pro / gemini-3.1-flash
deepseek-3.2, qwen3-coder-next, minimax-m2.1, …

Compatibility notes

logprobs — supported
tool_calls — supported (including parallel)
response_format=json_schema — supported
reasoning_effort — supported on Responses API
Multimodal input — passes through