fix: LLM_MODEL default to openrouter/deepseek/deepseek-v4-flash

LiteLLM requires openrouter/ prefix to route through openrouter API. Without it, deepseek/* models route to Deepseek native API and fail with the openrouter API key.
2026-07-07 06:09:31 +02:00
parent fcc9b22ec0
commit 88ddc21e64
2 changed files with 2 additions and 2 deletions
@@ -15,7 +15,7 @@ services:
      - PORT=${PORT:-8000}
      - LLM_PROVIDER=${LLM_PROVIDER:-openrouter}
      - LLM_API_KEY=${LLM_API_KEY}
-      - LLM_MODEL=${LLM_MODEL:-anthropic/claude-3.5-sonnet}
+      - LLM_MODEL=${LLM_MODEL:-openrouter/deepseek/deepseek-v4-flash}
      - LLM_API_BASE=${LLM_API_BASE:-}
      - MCP_SERVER_URL=${MCP_SERVER_URL:-http://mcp-tools:8501/mcp}
      - MCP_TIMEOUT=${MCP_TIMEOUT:-10}