One OpenAI-compatible endpoint for GPT, Claude, Gemini and DeepSeek (Python + Node examples)

Aliasghar Ramin — Sat, 24 Oct 2026 19:32:48 +0000

Most LLM projects end up talking to more than one vendor: GPT for one job, Claude for another, Gemini or DeepSeek when cost matters. Each vendor has its own SDK, key, billing account and rate limits. An OpenAI-compatible gateway removes most of that: one base URL, one key, and the model is just a string.

This post shows the pattern with Gisoo, the gateway we run (disclosure: I'm on the team). It exposes 680+ models behind the standard OpenAI API shape, so the official openai SDKs work unchanged. The same code works with any OpenAI-compatible gateway; only the base URL and key change.

1. List the models (no key needed)

curl -s https://gisoo.pro/api/v1/models | jq '.data | length'
# 682

curl -s https://gisoo.pro/api/v1/models \
  | jq -r '.data[] | select(.type=="chat") | .id' | head

Each entry has an id, an owned_by vendor and a type (chat, image, audio, embedding, video, music). Directly connected models use their own name (gpt-5-mini, deepseek-flash, gemini-3.6-flash); the rest carry an openrouter/ prefix (openrouter/anthropic/claude-sonnet-4.5).

2. Python: same client, three vendors

from openai import OpenAI

client = OpenAI(
    base_url="https://gisoo.pro/api/v1",
    api_key="sk-gisoo-v1-...",  # created in the Gisoo app
)

question = "Explain idempotency keys in two sentences."

for model in ["gpt-5-mini", "gemini-3.6-flash", "deepseek-flash"]:
    r = client.chat.completions.create(
        model=model,
        messages=[{"role": "user", "content": question}],
    )
    print(f"--- {model}\n{r.choices[0].message.content}\n")

Switching vendor is a one-word change. That makes it cheap to A/B models on your own prompts instead of trusting benchmarks.

3. Node.js with streaming

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gisoo.pro/api/v1",
  apiKey: process.env.GISOO_API_KEY,
});

const stream = await client.chat.completions.create({
  model: "openrouter/anthropic/claude-sonnet-4.5",
  messages: [{ role: "user", content: "Write a haiku about retries." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

Streaming is plain SSE in the OpenAI format, so existing UI code (Vercel AI SDK, LangChain, LiteLLM clients) keeps working.

4. A cheap fallback chain

Because every model sits behind the same endpoint, fallback is a loop, not three SDKs:

from openai import OpenAI, APIError

client = OpenAI(base_url="https://gisoo.pro/api/v1", api_key="sk-gisoo-v1-...")

def ask(messages, models=("deepseek-flash", "gemini-3.6-flash", "gpt-5-mini")):
    last = None
    for m in models:
        try:
            return m, client.chat.completions.create(model=m, messages=messages, timeout=60)
        except APIError as e:
            last = e  # vendor busy or refused: try the next one
    raise last

model, r = ask([{"role": "user", "content": "Summarise RFC 9110 in one line."}])
print(model, r.choices[0].message.content)

Order the list cheapest-first and you only pay for the expensive model when the cheap one fails.

5. Not only chat

The same key covers the other OpenAI endpoints:

Task	Endpoint
Chat / tools / JSON output	`POST /chat/completions`, `POST /responses`
Embeddings	`POST /embeddings`
Images	`POST /images/generations`
Speech-to-text / text-to-speech	`POST /audio/transcriptions`, `POST /audio/speech`
Video	`POST /videos`

There is also an Anthropic-compatible endpoint (https://gisoo.pro/api) for tools that only speak the Anthropic Messages API, and a remote MCP server (https://gisoo.pro/api/mcp) for Claude Code, Cursor and Cline.

Things to check with any gateway

Data handling. Ask whether prompts are stored. (Gisoo's API stores metadata such as model, tokens and cost, not request or response bodies.)
Pricing. Per-token prices should match or be close to the vendor's, and be visible per model before you call it.
Model IDs. Pin exact IDs in production; aliases can move.
Limits. Per-key rate limits (Gisoo's default is 60 requests/minute) and per-key spend caps are worth setting before you ship.

Why we built it

Gisoo started for developers and teams in Iran, who can't pay OpenAI, Anthropic or Google directly: credit is paid in local currency, and there is an Iran-optimised mirror at ir.gisoo.pro. The API itself is the standard one, so the code above runs from anywhere.

Docs (Persian, code is universal): https://gisoo.pro/docs. Questions and corrections are welcome in the comments.

DEV Community: Aliasghar Ramin