docs: clarify provider path limitations

This commit is contained in:
Ravi Tharuma
2026-03-27 11:13:08 +01:00
parent 224f0de353
commit 0ab977c236
4 changed files with 9 additions and 8 deletions
+2 -2
View File
@@ -74,13 +74,13 @@ CLIProxyAPI includes integrated support for [Amp CLI](https://ampcode.com) and A
- **Model mapping** to route unavailable models to alternatives (e.g., `claude-opus-4.5``claude-sonnet-4`)
- Security-first design with localhost-only management endpoints
When routing needs to stay deterministic, prefer the provider-specific paths over the merged `/v1/...` endpoints:
When you need the request/response shape of a specific backend family, use the provider-specific paths instead of the merged `/v1/...` endpoints:
- Use `/api/provider/{provider}/v1/messages` for messages-style backends.
- Use `/api/provider/{provider}/v1beta/models/...` for model-scoped generate endpoints.
- Use `/api/provider/{provider}/v1/chat/completions` for chat-completions backends.
This matters when `oauth-model-alias`, alias pools, or fallback mappings reuse the same client-visible model name across multiple backends. In those cases, `/v1/models` may show the merged alias view instead of the executor you intend to hit. Treat the provider-specific request path as the source of truth for backend selection.
These routes help you select the protocol surface, but they do not by themselves guarantee a unique inference executor when the same client-visible model name is reused across multiple backends. Inference routing is still resolved from the request model/alias. For strict backend pinning, use unique aliases, prefixes, or otherwise avoid overlapping client-visible model names.
**→ [Complete Amp CLI Integration Guide](https://help.router-for.me/agent-client/amp-cli.html)**