Model Gateway

Background

Influxion processes all model requests through a gateway service that implements the OpenAI Chat Completions API. All models on the Models page are accessible through the Influxion gateway, as are your own Model Set deployments.

Each model has a unique slug—or identifier—in the form provider/model-name. Model sets similarly have unique slugs in the form @username/model-set-name. Specify either slug in your request's model field, and we will route to an appropriate backend provider. See Quickstart simple request examples, and below for OpenAI SDK compatibility.

API Capabilities

The gateway supporst all functionality in the Chat Completions API, including:

• Streaming requests
• Function calling
• Tool use
• Different data modalities like files, audio, images, and video

OpenAI SDK Compatibility

The gateway supports using the OpenAI SDK in your preferred language (Python, JavaScript, .NET, Java, and Go). For example:

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["INFLUXION_API_KEY"],
    base_url="https://api.influxion.io/v1"
)

response = client.chat.completions.create(
    model="openai/gpt-5.1",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

import OpenAI from "openai";
const client = new OpenAI(
    apiKey: "${process.env.INFLUXION_API_KEY}",
    baseURL: "https://api.influxion.io/v1",
);

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

console.log(response.output_text);