Skip to main content
While aggregating all the major LLMs behind one interface, OpenPAI also provides the operations, billing and observability capabilities an enterprise-grade gateway needs.

​
Unified access

OpenAI-compatible protocol

Fully compatible with /v1/chat/completions, /v1/embeddings, /v1/images/generations, /v1/audio/*, /v1/responses, /v1/realtime and more.

Claude native protocol

Provides the /v1/messages endpoint with support for system prompts, tool use, vision input and thinking mode.

Gemini native protocol

Provides the /v1beta/models/{model}:generateContent endpoint with full support for multimodal input and function calling.

Format conversion

Automatic conversion between OpenAI ⇄ Claude / OpenAI → Gemini / Gemini → OpenAI formats.

​
Model coverage

CategoryRepresentative models
ChatGPT-5.5 / 5.4, o4-mini, Claude Opus 4.8, Claude Sonnet 4.6, Gemini 3.1 Pro / 3.5 Flash, DeepSeek-V3, Qwen3, GLM-4.6, etc.
Reasoninggpt-5.x (reasoning_effort), o3 / o4-mini, Claude *-thinking / Opus effort, gemini-3.1-pro-preview
VisionGPT-5.x, Claude 4.x, Gemini 3.x, Qwen-VL
Image generationgpt-image-2, DALL·E 3, Midjourney (Proxy / Plus), Nano Banana
AudioWhisper, TTS, gpt-realtime multimodal
VideoSora, Veo, Kling, etc.
Embeddings / reranktext-embedding-3-*, bge-*, Cohere, Jina Rerank
MusicSuno, Udio
See the full model list in the Models overview.

​
Billing & quota

  • Pay-as-you-go: tokens are converted at the upstream’s official multiplier, with lower rates on cache hits.
  • Per-token quota: set a spending limit, expiry and model scope individually for each API key.
  • Top-ups & invoices: manual top-ups assisted by a dedicated agent, with invoices on request.
See Billing for details.

​
High-availability routing

Multi-channel load

The same model can be bound to multiple upstream channels and split by weight.

Automatic retries

Upstream errors automatically fail over to a healthy channel, transparently to the client.

Rate limiting

Per-user / per-model RPM and TPM limits protect backend stability.

Real-time monitoring

The console offers dashboards for request volume, spend and error rate.

​
Advanced capabilities

  • Chain of thought: supports OpenAI reasoning_effort, Claude thinking and Gemini thinking_budget.
  • Function calling: OpenAI Tools / Claude Tool Use / Gemini Function Calling all interoperate across protocols.
  • Structured output: strictly constrain output with a response_format JSON Schema.
  • Multimodal input: images (URL / base64), PDF, audio chunks and more.
  • Streaming responses: SSE streams (Server-Sent Events), fully compatible with the OpenAI streaming protocol.

​
Accounts & logs

  • Sign in with email / GitHub / Discord / Telegram / LinuxDO / OIDC.
  • 2FA / WebAuthn / Passkey two-factor authentication.
  • Prompt and response content is not recorded — the console only lets you review each call’s model, token usage and billing details.
  • Self-hosted deployment is supported.