Document status
- Last reviewed: 2026-05-19
- Authorship: Drafted with AI assistance (GitHub Copilot, multi-model review) and reviewed by a human maintainer before publication.
- Sources: Based on public documentation — primarily docs.github.com, learn.microsoft.com, and official vendor blogs cited inline.
- Verify before acting: GitHub and Microsoft update product documentation continuously. Re-confirm against the live source pages before relying on this content for production decisions.
⚠️ Important — Critical update: billing model changes June 1, 2026Since this document was first written, GitHub announced a complete replacement of the premium-request billing model. Starting June 1, 2026, Copilot Business and Copilot Enterprise move from per-seat + premium-request allowances to a token-based metered model denominated in GitHub AI Credits (1 credit = $0.01 USD). See section 7 for full details.
Sections 1–7 of this document describe the request-based model that remains in effect through May 31, 2026. Existing customers should read both halves to plan the transition. Source: Usage-based billing for organizations and enterprises.
- 1. Executive summary
- 2. The new billing model in detail
- 3. Impact on an organization already on Copilot Business or Enterprise
- 4. Recommendations for existing Business / Enterprise customers
- 5. Primary references (all official GitHub documentation)
- 6. Provenance & validation history
- 7. New model effective June 1, 2026 — GitHub AI Credits
GitHub Copilot is no longer a flat per-seat product. As of mid-2025, GitHub introduced a two-layer billing model:
- Per-seat license — unchanged in concept ($19/user/month Business; $39/user/month Enterprise). Gives every user unlimited use of "included" models (currently GPT-5 mini, GPT-4.1, GPT-4o — note GPT-4.1 is on a published deprecation path as of May 7, 2026), plus a monthly allowance of premium requests.
- Premium-request usage — a metered allowance (300/user/month for Business, 1,000/user/month for Enterprise). When a user picks an "advanced" model (e.g. Claude Sonnet 4.5/4.6, Claude Opus 4.5–4.7, GPT-5.3-Codex, GPT-5.4/5.5, Gemini 2.5 Pro / 3.1 Pro / 3 Flash) or uses certain agentic features (Copilot cloud agent, Spark, Code Review with premium models, etc.), the request is multiplied by a model-specific factor and counted against the allowance. Overage is billed at $0.04 per premium request if the org admin has the "Premium request paid usage" policy enabled.
For an org that is already paying for Business or Enterprise seats, the practical impact is:
- No price increase on existing seats — the per-seat fee did not change.
- New variable line items can appear on the invoice if heavy users routinely pick premium models or use the Copilot coding agent.
- Two new admin levers must be configured: (a) the Premium request paid usage policy and (b) budgets (bundled or per-SKU). Budgets are the only hard cap that prevents runaway overage spend.
- From November 1, 2025, premium requests are split into three SKUs — Copilot premium requests, Spark premium requests, and Copilot cloud agent premium requests — for cleaner cost attribution.
- GitHub Enterprise Cloud with data residency or FedRAMP adds an additional +10% multiplier on premium requests routed through that compliant infrastructure (it does not create a separate flat charge).
- From June 1, 2026, this entire request-based model is replaced by GitHub AI Credits (token-metered, pooled at the billing entity). See section 7.
| Layer | What it covers | How it is billed |
|---|---|---|
| Seat license | Access to Copilot at all (completions, chat with included models, policies) | Flat per assigned user, monthly |
| Premium requests | Premium models + agentic features (chat, CLI, code review, extensions, Spaces, cloud agent, Spark) | Monthly allowance per seat; overage metered at $0.04/request |
| Plan | Seat price | Premium requests / user / month |
|---|---|---|
| Copilot Free | $0 | 50 |
| Copilot Pro | $10 | 300 |
| Copilot Pro+ | $39 | 1,500 |
| Copilot Business | $19 | 300 |
| Copilot Enterprise | $39 | 1,000 |
Sources: About billing for GitHub Copilot, Plans for GitHub Copilot, GitHub Copilot Enterprise GA announcement (Feb 27, 2024).
- June 18, 2025 — premium-request billing went live for paid Copilot plans on GitHub.com. Counters reset to zero.
- August 1, 2025 — same change took effect on GHE.com (data-resident Enterprise Cloud).
- November 1, 2025 — premium requests split into three dedicated SKUs (Copilot premium requests, Spark premium requests, Copilot cloud agent premium requests) for granular budgeting and reporting.
- April 20, 2026 — new sign-ups for Copilot Pro, Copilot Pro+, and Copilot Student temporarily paused.
- April 22, 2026 — new self-serve sign-ups for Copilot Business for organizations on GitHub Free and GitHub Team plans temporarily paused (Enterprise Cloud customers unaffected).
- June 1, 2026 — request-based billing is replaced by GitHub AI Credits (token-based) for Copilot Business and Copilot Enterprise. Copilot code review also begins consuming GitHub Actions minutes on this date.
Source: Requests in GitHub Copilot, GitHub Copilot premium requests (billing), Pausing new self-serve signups for GitHub Copilot Business, Changes to GitHub Copilot plans for individuals, Copilot code review will start consuming GitHub Actions minutes on June 1, 2026.
- Included models (GPT-5 mini, GPT-4.1, GPT-4o) on a paid plan → 0 premium requests (rate-limited but free).
- Any other model → 1 × multiplier premium requests per prompt. Multipliers vary by model; advanced reasoning models can be 5×, 7.5× (GPT-5.5), 15× (Claude Opus 4.7) or more (Claude Opus 4.6 fast mode preview is 30×). Codex coding models (GPT-5.3-Codex, GPT-5.2-Codex) and frontier coding/chat models (Sonnet 4.5/4.6, Gemini 2.5 Pro / 3.1 Pro, GPT-5.2/5.4) are 1×. Some lightweight models are <1× (Claude Haiku 4.5 = 0.33×, Gemini 3 Flash = 0.33×, GPT-5.4 mini = 0.33×, Grok Code Fast 1 = 0.25×, GPT-5.4 nano = 0.25×). Multipliers stack multiplicatively with the auto-select discount and the data-residency adder — e.g. Sonnet 4.6 with auto-select on a data-resident tenant ≈ 1 × 0.9 × 1.1 = 0.99×.
- Copilot cloud agent (incl. custom agents): 1 premium request per session (a session starts when you assign Copilot to an issue or prompt it to undertake a task), multiplied by the model rate. Each real-time steering comment in an active session also costs 1 × multiplier. Also consumes GitHub Actions minutes.
- Spark: each prompt costs a fixed 4 premium requests (not multiplier-based).
- Auto model selection in VS Code chat, Copilot CLI, or Copilot cloud agent on a paid plan: 10% multiplier discount (e.g. Sonnet 4.6 billed at 0.9× instead of 1×).
- Data residency / FedRAMP enforcement on GitHub Enterprise Cloud: +10% multiplier on every premium request. Data residency in both US and EU regions plus FedRAMP-authorized models reached GA on April 13, 2026 — see Data residency (US + EU) and FedRAMP-authorized models now available in Copilot.
- Tool calls an agent makes autonomously inside a single prompt do not each count — only the user prompt counts.
Source: Requests in GitHub Copilot — Model multipliers, GitHub Copilot with data residency — pricing changes.
If a user exceeds their monthly allowance and the admin has enabled overages, additional premium requests are billed at $0.04 USD each (after applying the model multiplier). Unused requests do not roll over; counters reset on the 1st of each month at 00:00:00 UTC.
Source: Requests in GitHub Copilot.
- Existing seat cost is unchanged. Business stays $19/seat/mo, Enterprise stays $39/seat/mo.
- Net-new variable cost appears only if users (a) opt into premium models, (b) use the Copilot coding agent / Spark, or (c) work in a data-resident or FedRAMP region (where the +10% multiplier applies).
- Worst-case unbounded spend is prevented only by setting a budget with "Stop usage when budget limit is reached" — the policy alone allows unlimited overage.
- Enterprise seats get 3.3× more allowance than Business (1,000 vs 300), which is often the deciding factor for upgrading heavy-AI teams rather than paying overage at $0.04/request.
| Scenario (per user / month) | Premium requests consumed | Overage cost @ $0.04 |
|---|---|---|
| Business seat, 250 Sonnet 4.6 prompts (1× multiplier) | 250 | $0 (within 300) |
| Business seat, 500 Sonnet 4.6 prompts | 500 | (500 − 300) × $0.04 = $8.00 |
| Business seat, 100 prompts on a 5× reasoning model | 500 | $8.00 |
| Business seat, 40 Claude Opus 4.7 prompts (15×) | 600 | (600 − 300) × $0.04 = $12.00 |
| Enterprise seat, 1,200 Sonnet 4.6 prompts | 1,200 | (1,200 − 1,000) × $0.04 = $8.00 |
| Enterprise seat, 200 cloud-agent sessions + 900 chat prompts (1×) | 1,100 | $4.00 + Actions minutes |
| Enterprise seat, 250 Spark prompts (fixed 4×) | 1,000 | $0 (exactly at allowance) |
Multipliers and model availability change frequently. Always verify against the current model-multiplier table before forecasting.
Existing admins now have new things to manage:
- Premium request paid usage policy (per AI product: Copilot, Spark, Copilot cloud agent). On by default — disable to hard-cap users at the included allowance.
- Budgets — bundled across all premium SKUs or per-SKU. Required as a real spend cap.
- Multi-license users — if a user has seats from more than one enterprise/standalone org, they must pick a "Usage billed to" entity, otherwise premium requests are blocked.
- Usage monitoring — new usage reports show per-user premium-request consumption, useful for identifying power users who might justify a Copilot Enterprise upgrade.
- Cost attribution — cost centers and the new per-SKU split (from Nov 1, 2025) allow chargeback to teams.
Source: Manage premium requests for your enterprise.
- Inline code completions with included models remain unmetered on paid plans (subject to standard rate limits).
- Chat with the included models (GPT-5 mini, GPT-4.1, GPT-4o) remains unmetered on paid plans.
- Seat assignment, SSO, audit log, content-exclusion, and other governance features are unchanged.
- If a user has both a Business and an Enterprise seat in the same enterprise, only the Enterprise seat is billed (no double billing).
- Decide your overage posture before users notice. Either (a) leave overages on with a budget cap, or (b) disable the Premium request paid usage policy to hard-cap at the included allowance.
- Set a bundled premium-request budget at enterprise level as a fail-safe, even if cost-center budgets exist.
- Educate users on multipliers and the included models. A user who defaults to GPT-5 mini or uses Auto model selection consumes 0–0.9× per prompt versus 5–15× for some reasoning models (GPT-5.5 = 7.5×, Claude Opus 4.7 = 15×).
- Pull a usage report monthly for the first few cycles. Identify the top-decile consumers — they are the candidates for upgrade to Copilot Enterprise (1,000 req/mo) or for coaching on model choice.
- Treat the Copilot cloud agent as a separate cost center — it draws from both premium requests (1/session) and GitHub Actions minutes, and has its own SKU since Nov 1, 2025.
- If you operate under data residency or FedRAMP, add the +10% multiplier to every forecast.
- Plan the AI Credits transition now. Download the new April 2026 usage reports from your billing dashboard (released May 12, 2026) to model your projected June 1, 2026 AI-credit consumption. See section 7.
- Note the Copilot code review change — starting June 1, 2026, code review consumes GitHub Actions minutes in addition to AI credits. Forecast Actions capacity accordingly.
- About billing for GitHub Copilot
- GitHub Copilot premium requests (billing concept)
- Requests in GitHub Copilot (model multipliers, allowances, dates)
- Subscription plans for GitHub Copilot
- Managing premium requests for your enterprise
- GitHub Copilot with data residency — pricing changes
- GitHub Copilot Enterprise GA announcement, Feb 27 2024
- Setting up budgets to control spending
- NEW — Usage-based billing for organizations and enterprises (effective June 1, 2026)
- NEW — Usage-based billing for individuals (effective June 1, 2026)
- NEW — Models and pricing for GitHub Copilot (per-token rates)
- NEW — Preparing your organization for usage-based billing
- NEW — Copilot billing preview tool (interactive AI-credit estimator)
- NEW — Mario Rodriguez — "Copilot is moving to usage-based billing" (announcement blog post)
- Copilot code review will consume GitHub Actions minutes from June 1, 2026 (changelog)
- Data residency (US + EU) and FedRAMP-authorized models GA — April 13, 2026 (changelog)
Generated: 2026-05-05 by GitHub Copilot CLI (Claude Opus 4.7, 1M context). Last re-validated: 2026-05-14 against live GitHub docs and the GitHub Copilot Changelog.
Caveat for budget decisions: Multipliers, included models, and AI-credit pricing change frequently. Before committing budget, re-verify against the live model-multiplier table, the Plans page, and (post-June 1) the Models and pricing reference.
| Date | Pass | Result |
|---|---|---|
| 2026-05-05 | Initial generation + 5 parallel LLM validators (Claude Sonnet 4.5, Haiku 4.5, GPT-5.5, 5.4, 5.3-Codex) fact-checking against docs.github.com and github.blog |
All technical claims verified after wording fixes (SKU naming, data-residency phrasing, Gemini model names) |
| 2026-05-14 | Single-agent freshness diff (Claude Opus 4.7) against current live docs | 10 findings (2 CRITICAL, 3 HIGH, 3 MEDIUM, 2 LOW) all applied. Largest: added section 7 (AI Credits) for the June 1, 2026 transition |
| 2026-05-14 | 3 parallel Researcher subagents on disjoint scopes (AI Credits / request-based / operational) re-checking against live sources | 55/58 verifiable claims PASS; 11 fixes applied (Mario Rodriguez announcement citation, GPT-5.3-Codex multiplier, billing preview tool, annual-plan migration options, +10% data-residency GA citation) |
To re-validate this document: re-fetch every URL in section 5 plus the GitHub Copilot Changelog for the period since the last re-validation date above, then diff against the claims in sections 1-5 and 7. Re-validate before any budget decision and at minimum monthly given the pace of GitHub Copilot pricing changes.
Important: Effective June 1, 2026, GitHub is replacing the premium-request model documented in sections 1–5 with a token-based GitHub AI Credits system for Copilot Business and Copilot Enterprise. Existing customers are auto-migrated; no admin action is required to migrate, but you should re-baseline budgets and policies before that date.
- Unit of billing: GitHub AI Credit. 1 AI credit = $0.01 USD.
- What it measures: actual tokens consumed by the model — input tokens (sent to the model), output tokens (generated by the model), and cached tokens (reused context). Each token has a per-token price set per model; the total is converted to AI credits.
- What still uses AI credits: Copilot Chat, Copilot CLI, Copilot cloud agent, Copilot Spaces, Spark, third-party coding agents.
- What does NOT use AI credits: Code completions and next-edit suggestions remain unlimited for all paid plans (same as today).
| License | Standard included AI credits / user / month | Equivalent USD value |
|---|---|---|
| Copilot Business | 1,900 | $19 |
| Copilot Enterprise | 3,900 | $39 |
Promotional period for existing customers (June 1 – September 1, 2026):
| License | Promo included AI credits / user / month |
|---|---|
| Copilot Business | 3,000 |
| Copilot Enterprise | 7,000 |
After Sept 1, 2026, the standard amounts above apply.
Unlike the per-user premium-request bucket, AI credits are pooled at the billing-entity level. An enterprise with 100 Copilot Business licenses gets a shared pool of 190,000 AI credits/month (not 100 individual buckets of 1,900). Power users can draw more; lighter users offset that consumption automatically. This is a meaningful operational improvement for teams with uneven AI usage.
- Adding licenses mid-cycle increases the pool immediately.
- Removing licenses mid-cycle does not shrink the pool until the start of the next cycle.
- Additional usage allowed: usage continues at published per-credit rates ($0.01/credit), billed to the org/enterprise.
- Additional usage not allowed: usage blocks until the next monthly cycle.
- Budget levels: enterprise, organization, cost center, user (NEW \u2014 user-level budgets are explicit in this model). A
$0user-level budget = no Copilot access for that user, even if the org pool has capacity. There is no automatic fallback to lower-cost models when a user budget is exhausted.
- Download the April 2026 usage report (released 2026-05-12) to understand your current premium-request consumption and project it into AI credits. The report exposes per-feature, per-user, per-model token consumption needed to forecast the new model.
- Decide your overage posture in the new world: allow additional usage with a budget, or block at the included pool.
- Set enterprise-, org-, cost-center-, and (NEW) user-level budgets in USD before the cutover. Existing premium-request budgets carry over automatically into AI-credit budgets per the official preparation guide, but you should re-baseline thresholds since the unit of measurement changes from requests to dollars-of-tokens. A
$0user-level budget completely blocks a user, even when the org pool has capacity. - Use the official Copilot billing preview tool to model your projected AI-credit consumption from your historical premium-request data before the June 1 cutover.
- Identify power users likely to be limited under the standard AI-credit allowance (Business 1,900/mo standard ≈ same dollar value as today's seat). Consider Enterprise upgrades or higher user-level budgets for them.
- Communicate the change to developers — model choice now directly affects token cost (not just a multiplier on a request count). Lighter models save more in this model than they do under request-based billing.
- Plan for Copilot code review consuming Actions minutes from June 1, 2026 — this is a separate cost line from AI credits. The change applies to Pro / Pro+ / Business / Enterprise; reviews on public repositories remain free.
For completeness \u2014 individuals also move to AI credits on June 1, 2026 with the following allowances:
| Plan | Price | Base credits | Flex allotment | Total monthly credits |
|---|---|---|---|---|
| Copilot Pro | $10 | 1,000 | 500 | 1,500 |
| Copilot Pro+ | $39 | 3,900 | 3,100 | 7,000 |
| Copilot Max (NEW) | $100 | 10,000 | 10,000 | 20,000 |
Copilot Free will continue to include 2,000 code completions per month plus a small AI-credits allowance and auto model selection.
Annual Pro / Pro+ subscribers will not auto-renew and have two options confirmed by current GitHub documentation:
- (a) Cancel and receive a prorated refund.
- (b) Wait to be downgraded to Copilot Free at renewal.
A previously mentioned third option — converting to monthly billing with prorated credits before expiration — is not present in the current
usage-based-billing-for-individualsdocumentation. Verify against the live billing settings UI before communicating to users.
Subscribers who continue on annual billing under the legacy request-based model will see model-multiplier increases on June 1, 2026 — see the official Model multipliers for annual plans table for exact pre/post values. Subscribers who originally purchased Pro or Pro+ through GitHub Mobile (iOS / Android) cannot purchase additional AI credits.
Source: Mario Rodriguez — "Copilot is moving to usage-based billing" (GitHub Blog, April 27, 2026), Usage-based billing for organizations and enterprises, Usage-based billing for individuals, Models and pricing for GitHub Copilot, Copilot billing preview tool.