Skip to main content
PipeLLM exposes native public routes and converter routes. Use this section when you need the exact path, headers, request format, error behavior, and rate limit rules for PipeLLM’s public API.

Public Endpoint Families

Request formatNative routeConverter routeUse this when
OpenAI Chat Completions/v1/chat/completions/openai/v1/chat/completionsUse the native route for OpenAI-compatible platforms. Use the converter route to keep OpenAI format while calling Anthropic or Gemini models.
OpenAI Responses/v1/responsesNot available yetUse the native route for OpenAI-compatible platforms. For cross-protocol calls today, use the OpenAI Chat Completions converter instead.
Anthropic Messages/v1/messages/anthropic/v1/messagesUse the native route for Anthropic-compatible platforms. Use the converter route to keep Anthropic format while calling OpenAI or Gemini models.
Gemini Generate Content/v1beta/models/{model}:generateContent/gemini/v1beta/models/{model}:generateContentUse the native route for Gemini platforms. Use the converter route to keep Gemini format while calling OpenAI or Anthropic models.
For the detailed routing rules and protocol mismatch behavior, see Routing & Protocols.

Authentication

All public routes use your PipeLLM API key with protocol-specific headers:
API FormatHeader
OpenAI CompatibleAuthorization: Bearer $PIPELLM_API_KEY
Anthropicx-api-key: $PIPELLM_API_KEY
Geminix-goog-api-key: $PIPELLM_API_KEY

Base URLs

Route typeBase URL
Native public routeshttps://api.pipellm.ai
OpenAI converterhttps://api.pipellm.ai/openai/v1
Anthropic converterhttps://api.pipellm.ai/anthropic
Gemini converterhttps://api.pipellm.ai/gemini

Start Here

List Models

Discover the model IDs available to your account

Routing & Protocols

Choose the correct free route or converter route

Errors

Understand error types, status codes, and retry behavior

Rate Limits

Review request limits, balance protection, and headers

Endpoint References

OpenAI Compatible

/v1/chat/completions and /v1/responses

Anthropic

/v1/messages

Gemini

/v1beta/models/{model}:generateContent