Logs

Query the inference log for auditing and billing reconciliation.

GET/v1/platforms/{platformId}/logs

Returns a paginated list of inference log entries for the platform.

Auth: Platform key.

Query Parameters

Name	Type	Required	Description
page	integer	Optional	Page number.Default: `1`
limit	integer	Optional	Items per page. Max 100.Default: `20`
model	string	Optional	Filter by model slug.
end_user_id	string	Optional	UUID. Filter to a single end user.

bash

curl https://api.assistiv.ai/v1/platforms/{platformId}/logs?page=1&limit=20 \
  -H "Authorization: Bearer sk-plat_your_key"

json

{
  "data": [
    {
      "id": "uuid",
      "platform_id": "uuid",
      "end_user_id": "uuid",
      "request_type": "chat.completion",
      "provider_id": "uuid",
      "model_id": "uuid",
      "provider_model_id": "gpt-4o-2024-08-06",
      "prompt_tokens": 25,
      "completion_tokens": 8,
      "total_tokens": 33,
      "latency_ms": 420,
      "estimated_cost_usd": "0.000175",
      "status": "success",
      "error_message": null,
      "token_count_method": "reported",
      "billing_status": "billed",
      "metadata": {},
      "created_at": "2026-04-08T10:30:00Z"}
  ],
  "total": 128,
  "page": 1,
  "limit": 20
}

Request Types

`request_type`	Written by	Emitted per
`chat.completion`	Inference backend	One per `/v1/chat/completions` call
`response`	Inference backend	One per agent-loop iteration within `/v1/responses`
`agent`	Inference backend	One per agent-model call (LangGraph path)
`mcp_tool`	MCP service	One per executed MCP tool call (paid path only)

Analytics Guidance

⚠Row count is not request count

Don't count rows as “requests” — you'll inflate by 2-3x on MCP users. Group by timestamp clusters or request IDs.
Sum estimated_cost_usd across all request types to reconcile against wallet delta.
A single /v1/responses call with MCP tools can produce multiple rows (typically 2x response + 1x mcp_tool = 3 rows for one user-facing request).