Azure Pricing
Estimate Microsoft Copilot Studio message and action costs in USD before you commit to agent features or tenant grounding.
Overview
Azure Pricing is an agent skill for the Validate phase that explains Copilot Studio credit rates and helps estimate per-message and per-action spend in USD.
Install
npx skills add https://github.com/github/awesome-copilot --skill azure-pricingWhat is this skill?
- Maps Copilot Credits at 1 credit = $0.01 USD with a March 2026 rate table fallback
- Covers classic vs generative answers, agent actions, tenant graph grounding, and gen-AI tool tiers
- Points to live Microsoft docs, the Copilot Studio estimator, and the licensing guide as preferred sources
- Documents per-unit billing for agent flows (13 credits per 100 flow actions) and content processing (8 per page)
- 1 Copilot Credit = $0.01 USD
- Billing rate table cached snapshot last updated March 2026
- 10 billing rows for features including grounding and gen-AI tool tiers
Adoption & trust: 4.4k installs on skills.sh; 34.6k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You are designing a Copilot Studio agent but cannot translate feature choices into predictable Copilot Credit and dollar costs.
Who is it for?
Indie builders prototyping Microsoft Copilot Studio agents who need a quick billing cheat sheet plus links to authoritative pricing pages.
Skip if: Teams that only need generic Azure VM or storage pricing without Copilot Studio message-level billing.
When should I use this skill?
You need Copilot Studio per-response, per-action, or per-page rates while scoping or reviewing an agent design.
What do I get? / Deliverables
You leave with unit rates, feature definitions, and official estimator URLs so you can compare grounding and model tiers against a budget before build-out.
- Credit-to-USD breakdown for chosen features
- Links to official estimator and licensing guide
Recommended Skills
Journey fit
Cost estimation belongs on the validate shelf because builders need billing math while scoping Copilot Studio agents, not after production incidents. Pricing subphase is the canonical home for credit rates, per-response units, and estimator links tied to licensing decisions.
How it compares
Use as a Copilot Studio–specific rate card inside the agent, not as a substitute for the official Microsoft agent usage estimator when you need scenario-based totals.
Common Questions / FAQ
Who is azure-pricing for?
Solo builders and small teams shipping or scoping agents on Microsoft Copilot Studio who must reason about credits before enabling grounding, flows, or premium gen-AI tools.
When should I use azure-pricing?
During validate and pricing work when you compare classic vs generative answers, agent action counts, or tenant graph grounding; also during build planning when a feature toggle would change per-message cost.
Is azure-pricing safe to install?
Treat it as documentation-heavy reference material; review the Security Audits panel on this Prism page and prefer live fetches to Microsoft URLs rather than relying only on cached tables.
SKILL.md
READMESKILL.md - Azure Pricing
# Copilot Studio — Billing Rates & Estimation > Source: [Billing rates and management](https://learn.microsoft.com/en-us/microsoft-copilot-studio/requirements-messages-management) > Estimator: [Microsoft agent usage estimator](https://microsoft.github.io/copilot-studio-estimator/) > Licensing Guide: [Copilot Studio Licensing Guide](https://go.microsoft.com/fwlink/?linkid=2320995) ## Copilot Credit Rate **1 Copilot Credit = $0.01 USD** ## Billing Rates (cached snapshot — last updated March 2026) **IMPORTANT: Always prefer fetching live rates from the source URLs below. Use this table only as a fallback if web fetch is unavailable.** | Feature | Rate | Unit | |---|---|---| | Classic answer | 1 | per response | | Generative answer | 2 | per response | | Agent action | 5 | per action (triggers, deep reasoning, topic transitions, computer use) | | Tenant graph grounding | 10 | per message | | Agent flow actions | 13 | per 100 flow actions | | Text & gen AI tools (basic) | 1 | per 10 responses | | Text & gen AI tools (standard) | 15 | per 10 responses | | Text & gen AI tools (premium) | 100 | per 10 responses | | Content processing tools | 8 | per page | ### Notes - **Classic answers**: Predefined, manually authored responses. Static — don't change unless updated by the maker. - **Generative answers**: Dynamically generated using AI models (GPTs). Adapt based on context and knowledge sources. - **Tenant graph grounding**: RAG over tenant-wide Microsoft Graph, including external data via connectors. Optional per agent. - **Agent actions**: Steps like triggers, deep reasoning, topic transitions visible in the activity map. Includes Computer-Using Agents. - **Text & gen AI tools**: Prompt tools embedded in agents. Three tiers (basic/standard/premium) based on the underlying language model. - **Agent flow actions**: Predefined flow action sequences executed without agent reasoning/orchestration at each step. ### Reasoning Model Billing When using a reasoning-capable model: ``` Total cost = feature rate for operation + text & gen AI tools (premium) per 10 responses ``` Example: A generative answer using a reasoning model costs **2 credits** (generative answer) **+ 10 credits** (premium per response, prorated from 100/10). ## Estimation Formula ### Inputs | Parameter | Description | |---|---| | `users` | Number of end users | | `interactions_per_month` | Average interactions per user per month | | `knowledge_pct` | % of responses from knowledge sources (0-100) | | `tenant_graph_pct` | Of knowledge responses, % using tenant graph grounding (0-100) | | `tool_prompt` | Average Prompt tool calls per session | | `tool_agent_flow` | Average Agent flow calls per session | | `tool_computer_use` | Average Computer use calls per session | | `tool_custom_connector` | Average Custom connector calls per session | | `tool_mcp` | Average MCP (Model Context Protocol) calls per session | | `tool_rest_api` | Average REST API calls per session | | `prompts_basic` | Average basic AI prompt uses per session | | `prompts_standard` | Average standard AI prompt uses per session | | `prompts_premium` | Average premium AI prompt uses per session | ### Calculation ``` total_sessions = users × interactions_per_month ── Knowledge Credits ── tenant_graph_credits = total_sessions × (knowledge_pct/100) × (tenant_graph_pct/100) × 10 generative_answer_credits = total_sessions × (knowledge_pct/100) × (1 - tenant_graph_pct/100) × 2 classic_answer_credits = total_sessions × (1 - knowledge_pct/100) × 1 ── Agent Tools Credits ── tool_calls = total_sessions × (prompt + computer_use + custom_connector + mcp + rest_api) tool_credits = tool_calls × 5 ── Agent Flow Credits ── flow_calls = total_sessions × tool_agent_flow flow_credits = ceil(flow_calls / 100) × 13 ── Prompt Modifier Credits ── basic_credits = ceil(total_sessions × prompts_basic / 10) × 1 standard_credits = ceil(total_sessions × prompts_standard / 10) × 15 premium_credits = ceil(total_ses