Wichtig
On June 1, 2026, GitHub moved to usage-based billing. The model multipliers in this article apply only to Copilot Pro and Copilot Pro+ subscribers on an existing annual plan who remained on the legacy premium request-based billing model after June 1, 2026.
To learn more about these billing changes, including what your options are as an existing Copilot Pro and Copilot Pro+ subscriber on an annual plan, see What changed with Copilot billing (legacy).
Under the legacy premium request-based billing model, each model has a premium request multiplier, based on its complexity and resource usage. Your premium request allowance is deducted according to this multiplier.
Model multipliers are a concept specific to the legacy premium request-based billing system, and do not apply to GitHub's new usage-based billing model.
The models included with Copilot plans are subject to change.
Model multipliers and costs are subject to change.
Hinweis
If you use Automatische Modellauswahl in Copilot-Chat, Copilot CLI, or Copilot-Cloud-Agent, you qualify for a 10% discount. For example, if a model has a multiplier of 1x you'll be billed at 0.9x instead.
Model multipliers
The following table shows the model multipliers per supported model.
Hinweis
The multiplier for these models are subject to change.
- Claude Sonett 4.6
- GPT-5.4 mini
| Model | Multiplier |
|---|---|
| Claude Haiku 4.5 | 0.33 |
| Claude Opus 4.5 | 15 |
| Claude Opus 4.6 | 27 |
| Claude Opus 4.7 | 27 |
| Claude Opus 4.8 | 27 |
| Claude Sonnet 4.5 | 6 |
| Claude Sonnet 4.6 | 9 |
| Gemini 2.5 Pro | 1 |
| Gemini 3 Flash | 0.33 |
| Gemini 3 Pro | 6 |
| Gemini 3.1 Pro | 6 |
| Gemini 3.5 Flash | 14 |
| GPT-4o | 0.33 |
| GPT-4o mini | 0.33 |
| GPT-4.1 | 1 |
| GPT-5.1 | 3 |
| GPT-5.1-Codex | 3 |
| GPT-5.1-Codex-Mini | 0.33 |
| GPT-5.1-Codex-Max | 3 |
| GPT-5.2 | 3 |
| GPT-5.2-Codex | 3 |
| GPT-5.3-Codex | 6 |
| GPT-5.4 | 6 |
| GPT-5.4 mini | 6 |
| GPT-5.5 | 57 |
| GPT-5 mini | 0.33 |
| Raptor mini | 0.33 |
Model multiplier for Copilot Codeüberprüfung
Copilot Codeüberprüfung has a model multiplier of 13. This means each time Copilot reviews a pull request or reviews code in your IDE, your monthly quota of Copilot premium requests is reduced by 13.
Further reading
- To learn more about premium requests, see Requests in GitHub Copilot (legacy).
- To understand more about how the new usage-based billing model works, see Nutzungsbasierte Abrechnung für Einzelpersonen.