Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.tensormesh.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
April 29, 2026

Yotta on On-Demand Yotta is now available as a cloud provider for on-demand deployments, joining Nebius. Pick Yotta in the Cloud Provider step when launching a new on-demand deployment. (Model Deployment)
Account Deletion — You can now delete your own account from Management → Account. Account deletion requires email confirmation and is permanent.Billing Transaction Details — Transaction details on the Billing page now show a deeper breakdown.

​
April 15, 2026

Serverless Inference Run models via API with no infrastructure to manage. 8 models available at launch with pay-per-token pricing. Track per-model token usage and costs under Billing → Serverless Usage. The API is OpenAI-compatible — point any existing SDK to https://serverless.tensormesh.ai. (Serverless Inference) Auto Scaling for On-Demand (Beta) On-demand deployments now support auto scaling. Toggle between fixed and auto scaling when deploying, and configure min/max replicas, scale-to-zero delay, and stabilization windows to match your traffic patterns. This feature is currently in beta — behavior and configuration options may change. (Model Deployment) Tensormesh Demos A new Demos section with interactive benchmarks. The first demo — Ask the Document — fires 20 questions against a shared document prefix so you can watch KV cache acceleration in real time across TTFT, E2E latency, and inter-token latency. (Demos) CLI Documentation A new CLI tab in the docs with guides and a full command reference for the tm CLI tool — covering installation, authentication, inference, model management, billing, and admin workflows. (CLI) Python SDK A new Python SDK tab with guides for the tensormesh package — covering sync and async clients, inference (serverless and on-demand), control plane resources, and migration from OpenAI/Fireworks. (Python SDK) API & SDK Reference Documentation Full interactive API & SDK docs for all Tensormesh endpoints with an in-browser playground and code examples in cURL, Python, and JavaScript. (API & SDK Reference)
Email Notification Preferences — Toggle email notifications for deployment updates from Management → User Profile.Support Ticket Attachments — You can now attach files when creating support tickets.Running Requests Metric — A new Running Requests chart is available in deployment metrics, showing real-time concurrent request volume over time.Quick Actions on Dashboard — Six quick action cards on the Overview page for faster navigation to common operations.

​
March 17, 2026

MiniMax-M2.5 Added MiniMaxAI/MiniMax-M2.5 is now available as a preloaded model for on-demand deployments. Built on a 228B-parameter Mixture-of-Experts architecture with a 196K context window, it excels at advanced reasoning, coding, and building autonomous systems that combine tool orchestration with large-scale information processing. Select it from the model library when configuring a new deployment.
Cost Saving Breakdown — Cost Saving page now displays a step-by-step savings breakdown with calculation formulas.Dedicated Observability Page — Monitor deployment metrics in one view at Operations → Observability.Model Chatbot Moved — Chatbot now lives at Operations → Chatbot, grouping all operational tools together.Browser Notifications — Notification preferences can now be configured from the User Profile page.