Skip to main content

Provider Compatibility

Provider compatibility depends on both the caller-facing endpoint and the upstream provider configuration behind the model alias. A model can work on a broad chat endpoint and still be rejected on a provider-specific endpoint.

AISIX has two compatibility layers:

LayerPurpose
Adapter familiesDecide how chat-style requests are encoded for upstream providers. See Adapter Protocol Families.
Endpoint rulesDecide whether a specific proxy route accepts the selected model alias.

Check both layers when planning a route. The adapter tells AISIX how to talk to the upstream provider; the endpoint's own rules decide whether that proxy route supports the selected provider or adapter family.

Endpoint Compatibility

Use the caller's API format and provider support requirements to choose a proxy route.

NeedRouteProvider support
Broad chat compatibility/v1/chat/completionsOpenAI, Anthropic, Bedrock, Vertex AI, Azure OpenAI, and OpenAI-compatible providers through their configured adapter.
Anthropic-style clients/v1/messagesAnthropic upstreams natively; non-Anthropic upstreams through translation with limited feature coverage.
Anthropic token counting/v1/messages/count_tokensAnthropic-backed models only.
Streaming chat/v1/chat/completions or /v1/messages with stream: trueSame provider support as the chosen endpoint. Streaming uses the first selected target and does not fail over mid-stream.
Embeddings/v1/embeddingsOpenAI adapter support. Other adapters return 501 not_implemented unless support is added later.
OpenAI Responses API/v1/responsesModels whose configured provider is OpenAI. OpenAI-compatible vendors are not automatically supported.
Image generation/v1/images/generationsModels whose configured provider is OpenAI.
Audio/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speechOpenAI-style upstream audio routes. AISIX forwards the audio format; it does not translate audio across provider families.
Rerank/v1/rerankOpenAI, Cohere, and Jina provider values.
Provider-native routes/passthrough/:provider/*restAny provider value with an accessible model and provider key, with limited gateway normalization.

Endpoint Rules

The compatibility matrix is the primary route reference. The rules below clarify cases where provider identity, adapter family, and endpoint behavior differ.

  • Chat completions is the broadest normalized route. For non-OpenAI upstreams, the provider-facing request can still use Anthropic, Bedrock, Vertex AI, Azure OpenAI, or another adapter-specific format behind the gateway.
  • Responses and image generation are OpenAI-provider routes. An OpenAI-compatible vendor can use the OpenAI adapter for chat completions and still be rejected on these routes when its provider value is not openai.
  • Embeddings and audio are OpenAI-style forwarding routes. They depend on the resolved adapter and upstream route support rather than translating across provider families.
  • Rerank uses a route-specific provider allowlist. Accepted provider values are openai, cohere, and jina.
  • Anthropic Messages supports native Anthropic upstreams and translated non-Anthropic upstreams. Token counting requires an Anthropic-backed model.
API7.ai Logo

The digital world is connected by APIs,
API7.ai exists to make APIs more efficient, reliable, and secure.

Sign up for API7 newsletter

Product

API7 Gateway

SOC2 Type IIISO 27001HIPAAGDPRRed Herring

Copyright © APISEVEN PTE. LTD 2019 – 2026. Apache, Apache APISIX, APISIX, and associated open source project names are trademarks of the Apache Software Foundation