OpenAI-Compatible API

FIM Gate exposes an OpenAI-compatible interface for the vast majority of models: the request and response structures match the OpenAI API, so you only need to swap the base URL to FIM Gate and the same code can call GPT, Claude, Gemini, and models from other providers.

Connection details

Minimal example

curl https://api.gate.fim.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $FIM_API_KEY" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "user", "content": "Introduce yourself in one sentence"}
    ]
  }'

To switch models, just change the model field — for example to claude-sonnet-4-5 or gemini-2.5-pro — and the request structure stays the same.

Using the OpenAI SDK

Any OpenAI SDK that supports a custom base_url works out of the box:

from openai import OpenAI

client = OpenAI(
    api_key="$FIM_API_KEY",
    base_url="https://api.gate.fim.ai/v1",
)

resp = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.FIM_API_KEY,
  baseURL: "https://api.gate.fim.ai/v1",
});

const resp = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(resp.choices[0].message.content);

Included endpoints

Image and audio endpoints are also available:

• /v1/images/generations — text-to-image, supports dall-e-2, dall-e-3, gpt-image-1, gemini-2.5-flash-image, gemini-3-pro-image-preview, gemini-3.1-flash-image-preview; see Images API
• /v1/audio/speech — text-to-speech, supports tts-1, tts-1-hd, gpt-4o-mini-tts, gemini-2.5-flash-preview-tts, gemini-2.5-pro-preview-tts; see Audio API
• /v1/audio/transcriptions — speech-to-text, supports whisper-1; see Audio API

Choosing between Chat Completions and Responses

• If you have existing code built on Chat Completions, or your third-party framework only supports that format: keep using /v1/chat/completions.
• If you need OpenAI's built-in tools (such as web search) or reasoning effort control: use /v1/responses.

Both share the same API key and credit balance, so you can mix and match freely.