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:
| Layer | Purpose |
|---|---|
| Adapter families | Decide how chat-style requests are encoded for upstream providers. See Adapter Protocol Families. |
| Endpoint rules | Decide 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.
| Need | Route | Provider support |
|---|---|---|
| Broad chat compatibility | /v1/chat/completions | OpenAI, Anthropic, Bedrock, Vertex AI, Azure OpenAI, and OpenAI-compatible providers through their configured adapter. |
| Anthropic-style clients | /v1/messages | Anthropic upstreams natively; non-Anthropic upstreams through translation with limited feature coverage. |
| Anthropic token counting | /v1/messages/count_tokens | Anthropic-backed models only. |
| Streaming chat | /v1/chat/completions or /v1/messages with stream: true | Same provider support as the chosen endpoint. Streaming uses the first selected target and does not fail over mid-stream. |
| Embeddings | /v1/embeddings | OpenAI adapter support. Other adapters return 501 not_implemented unless support is added later. |
| OpenAI Responses API | /v1/responses | Models whose configured provider is OpenAI. OpenAI-compatible vendors are not automatically supported. |
| Image generation | /v1/images/generations | Models whose configured provider is OpenAI. |
| Audio | /v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech | OpenAI-style upstream audio routes. AISIX forwards the audio format; it does not translate audio across provider families. |
| Rerank | /v1/rerank | OpenAI, Cohere, and Jina provider values. |
| Provider-native routes | /passthrough/:provider/*rest | Any 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, andjina. - Anthropic Messages supports native Anthropic upstreams and translated non-Anthropic upstreams. Token counting requires an Anthropic-backed model.