/
/AI Proxy Swagger API
DocsSign in
Sign in
  • APIs
  • Generators
  • Stacks
  • Projects
  • Docs
  • History
  • Schema
Checked 2h ago · Updated 1w ago
channel12
channels8
dashboard7
embedmcp6
group15
groups7
log4
logs6
mcp20
misc1
model8
modelconfig9
monitor13
  • getGet all channel model error rates
  • deleteClear all model errors
  • getGet all banned model channels
  • postBatch get runtime metrics for api key rows
  • getGet model runtime metrics for a group
  • getGet summary metrics for multiple groups
  • getGet token runtime metrics for a group
  • getGet token-model runtime metrics for a group
  • getGet models error rate
  • getGet runtime metrics for models and channels
  • getGet channel model error rates
  • deleteClear channel all model errors
  • deleteClear channel model errors
option6
relay31
token8
tokens9
  • getTest Public MCP SSE Server
  • getHost MCP Streamable Server
  • postHost MCP Streamable Server
  • deleteHost MCP Streamable Server
  • getGroup MCP Streamable Server
  • postGroup MCP Streamable Server
  • deleteGroup MCP Streamable Server
  • getGroup MCP SSE Server
  • getPublic MCP Streamable Server
  • postPublic MCP Streamable Server
  • deletePublic MCP Streamable Server
  • getPublic MCP SSE Server
  • postMCP SSE Message
  • getPublic MCP SSE Server
monitor

Get model runtime metrics for a group

Returns runtime rpm/tpm metrics grouped by model in a group

get/api/monitor/group_model_metrics/{group}

Path parameters

groupstring required

Group ID

Response

OK

messagestring
successboolean

Changes