docs: clarify provider-specific routing for aliased models

This commit is contained in:
Ravi Tharuma
2026-03-27 10:53:09 +01:00
parent d42b5d4e78
commit d54de441d3
4 changed files with 27 additions and 0 deletions

View File

@@ -281,6 +281,9 @@ nonstream-keepalive-interval: 0
# These aliases rename model IDs for both model listing and request routing.
# Supported channels: gemini-cli, vertex, aistudio, antigravity, claude, codex, qwen, iflow, kimi.
# NOTE: Aliases do not apply to gemini-api-key, codex-api-key, claude-api-key, openai-compatibility, vertex-api-key, or ampcode.
# NOTE: Because aliases affect the merged /v1 model list and merged request routing, overlapping
# client-visible names can become ambiguous across providers. When you need deterministic backend
# selection, prefer /api/provider/{provider}/... instead of the generic /v1/... endpoints.
# You can repeat the same name with different aliases to expose multiple client model names.
# oauth-model-alias:
# gemini-cli: