One key — access to 100+ models for text, images, video and audio. OpenAI-compatible request format.
No need to register with each provider separately.
A familiar request format — easy migration.
Pay only for the tokens and generations you use.
Embed AI into bots, services and internal tools.
One shared balance for every model — no subscriptions, no minimum payments.
In your dashboard, under «Profile». Create as many keys as you need — one per project.
POST to https://gptunnel.ru/v1/chat/completions with an Authorization header and the model name.
curl https://gptunnel.ru/v1/chat/completions \
-H "Authorization: <YOUR_API_KEY>" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Hello!"}]
}'
Any OpenAI-compatible library works the same way — just point base_url at https://gptunnel.ru/v1 and pass your key.
Top language models in the OpenAI-compatible format: streaming, message history, function calling.
Generate and edit images with Flux, Imagen, GPT Image and more.
Text-to-video and image-to-video: an async job you pick up later by its id.
Speech synthesis, music and transcription — voice-overs, phone bots, meeting notes.
Text vectorisation and a hosted knowledge base — search your own documents without running the infrastructure.
Check user-generated text before you publish it or pass it to a model.
Employees, access rights and spend per key — managed through the API and the dashboard.
Get a key and connect AI models in minutes.