Send chat, completion, and embedding requests through a single OpenAI-compatible endpoint. Switch between providers without rewriting client code.
Обзор возможностей
1 API
OpenAI-compatible endpoint
multi
model providers
unified
request schema
Ключевые ценностные моменты для практических рабочих процессов.
Преимущество
01
Drop-in OpenAI compatibility
Reuse the existing OpenAI SDK, libraries, and tooling. Only the base URL and API key change.
Преимущество
02
Single integration surface
One contract for chat, streaming, function calling, and embeddings across every supported provider.
Преимущество
03
Vendor decoupling
Move workloads between providers from configuration alone. No code change required.
Простой путь из 3 шагов для интеграции этой возможности в вызовы шлюза, политики маршрутизации и контроль биллинга.
Шаг 1
Create an API key
Issue a key under your account or organization with scoped permissions.
Шаг 2
Point your SDK to the gateway
Set the base URL to the DeepToken endpoint and continue using OpenAI-compatible request shapes.
Шаг 3
Select a model
Pass any supported model id and let the gateway resolve provider, region, and quota.
Yes. Standard chat, completion, embedding, and streaming endpoints follow the OpenAI request and response schema.
Yes. One API key can route to every model your plan and organization permits.
Следующий шаг
Начните с документации, каталога моделей или панели управления и проверьте эту возможность на реальном трафике.