The request "model-usage" is ambiguous: it could mean tracking or reporting AI model usage, or choosing a model to use. Products below cover model usage tracking and monitoring (Atlas Cloud, Traceloop, Marrow AI), model access APIs (OpenAI, Atlas Cloud, Ollama), and model-usage metering on Cloudflare; their relevance depends on which sense is meant.
A question back: Do you mean tracking and reporting how much an AI model is used (tokens, requests, cost), or choosing which model to use for a task?
- 1
Atlas Cloud APIatlascloud.aifound in code, not yet checked
Atlas Cloud exposes an action to get daily model usage buckets (requests, tokens, image/video counts) for an API key over a UTC date range 14.
for agents: atlas_get_model_usage · atlas_get_model_info · atlas_list_models
- 2
Tracelooptraceloop.comfound in code, not yet checked
Traceloop lists LLM models in use with usage statistics, returns per-model performance stats, and aggregates LLM token usage over a time period 16.
+1 community tools built for it
for agents: list_llm_models · get_llm_model_stats · get_llm_usage
- 3
Marrow AIgetmarrow.aifound in code, not yet checked
Marrow AI records compact model token usage for value proof when the harness exposes provider and model token counts.
official:package · Marrow AI: Control Layer for AI Agents
for agents: marrow_model_usage · marrow_mode_recommend · marrow_orient
- 4
OpenAI APIopenai.comverified and signed
The OpenAI API lists the models an account can use and retrieves a model's owner and permissioning details 12.
official:API · OpenAI APISDK · openailibrary · OpenAIskill · babysit-prSDK · openai+163 community tools built for it
for agents: retrieveModel · list_models · listModels
- 5
Cloudflarecloudflare.comverified and signed
Cloudflare exposes actions to fetch and replace a Worker script's usage model 13.
official:MCP server · @cloudflare/mcp-server-cloudflareCLI · cloudflaredskill · cloudflareskill · durable-objects+259 community tools built for it
for agents: worker-script-update-usage-model · worker-script-fetch-usage-model · workers-ai-search-model
Sources
- 3Cloudflare: Build for the agent eracloudflare.com · read 2026-10-29
- 4400+ AI Models, One API for Image, Video, Audio and Chat | Atlas Cloudatlascloud.ai · read 2026-10-30
- 6Traceloop - LLM Reliability Platformtraceloop.com · read 2026-10-30
- 9Marrow AI: AI Agent Governance and Control Layergetmarrow.ai · read 2026-10-29
- 12OpenAI API: declares "retrieveModel" (the record we read and signed)unfragile.ai · read 2026-10-24
- 13Cloudflare API: declares "worker-script-update-usage-model" (the record we read and signed)unfragile.ai · read 2026-10-24
- 14Atlas Cloud MCP Server (Image / Video / LLM APIs): declares "atlas_get_model_usage" (the record we read)github.com · read 2026-10-24
- 16opentelemetry-mcp-server: declares "list_llm_models" (the record we read)github.com · read 2026-10-24
For agents: the 10 actions behind this answer
model-recommendation · model-recommendation verified and signed
Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and cost-efficiency
retrieveModel · OpenAI API verified and signed
Retrieves a model instance, providing basic information about the model such as the owner and permissioning.
worker-script-update-usage-model · Cloudflare API verified and signed
Replace Worker Script Usage Model
atlas_get_model_usage · Atlas Cloud MCP Server (Image / Video / LLM APIs) found in code, not yet checked
Get daily model usage buckets (requests, tokens, image/video counts) for the authenticated API key over a UTC date range. Omitting group_by returns total daily buckets. Use group_by to break usage down by model_type, model, and/or api_key. Args: - start_date (string, required): Inclusive UTC start d
· Ollama website read, tools not yet checked
Ollama is the easiest way to run and build with open AI models locally or in the cloud on macOS, Windows, and Linux.
list_llm_models · opentelemetry-mcp-server found in code, not yet checked
List all LLM models being used with usage statistics.
embedding · sentence-transformers verified and signed
api · ghapi verified and signed
marrow_model_usage · Marrow found in code, not yet checked
Record compact model token usage for value proof. Use when the harness exposes provider/model token counts. Do not send raw prompts, completions, tool logs, secrets, or customer content.
sagemaker-ai · sagemaker-ai verified and signed
Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.