Chat completions, audio transcription, document analysis, and function calling — through a single OpenAI-compatible REST API. Existing OpenAI integrations work out of the box.
import OpenAI from "openai";
const client = new OpenAI({
apiKey: "VANTERO_API_KEY",
baseURL: "https://api.vantero.chat/v1",
});
const response = await client.chat.completions.create({
model: "gpt-5",
messages: [
{ role: "user", content: "Hallo!" },
],
});
console.log(response.choices[0].message.content);Create an API key, set the base URL, send your first request.
Generate a new key in the Vantero dashboard under API Keys. Optionally restrict it to specific models.
Change the base URL to https://api.vantero.chat/v1. The rest of your code stays the same.
Set the model parameter to the desired model (e.g. gpt-5, claude-sonnet-4-5, gemini-2.5-pro) and send the request.
All endpoints follow the OpenAI format and are compatible with existing SDKs.
/v1/chat/completionsChat completions with streaming, function calling, and JSON mode
/v1/modelsRetrieve all available models with capabilities
/v1/audio/transcriptionsTranscribe audio files (M4A, MP3, WAV, WebM)
/v1/filesUpload files for chat context (PDF, DOCX, XLSX)
/v1/files/{file_id}Retrieve file metadata and processing status
/v1/files/{file_id}/extractDocument extraction with table analysis and summarization
The official OpenAI SDK works directly — just change the base URL and API key. Existing code runs immediately.
Chat completions, audio transcription, document extraction, and function calling — all through one API.
Create as many API keys as you need, restrict them to specific models, and track usage per key.
Server-sent events for real-time streaming. JSON mode for structured output with schema validation.
Upload, extract, and analyze PDFs, spreadsheets, and documents via chat.
Speech to text in M4A, MP3, WAV, WebM, FLAC, OGG, and OPUS. With timestamps and language detection.
Create an API key and get started in minutes.