Copilot supports multiple AI models with different capabilities. The model you choose affects the quality and relevance of responses by Copilot Chat and Copilot code completion. Some models offer lower latency, while others offer fewer hallucinations or better performance on specific tasks. This guide helps you pick the best model based on your task, not just model names.
Note
Different models have different premium request multipliers, which can affect how much of your monthly usage allowance is consumed. For details, see Understanding and managing requests in Copilot.
Use this table to find a suitable model quickly, see more detail in the sections below.
| Model | Task area | Excels at (primary use case) | Additional capabilities |
|---|---|---|---|
| GPT-4.1 | General-purpose coding and writing | Fast, accurate code completions and explanations | Agent mode, visual |
| GPT-4.5 | Deep reasoning and debugging | Multi-step reasoning and complex code generation | Reasoning |
| GPT-4o | General-purpose coding and writing | Fast completions and visual input understanding | Agent mode, visual |
| o1 | Deep reasoning and debugging | Step-by-step problem solving and deep logic analysis | Reasoning |
| o3 | Deep reasoning and debugging | Multi-step problem solving and architecture-level code analysis | Reasoning |
| o3-mini | Fast help with simple or repetitive tasks | Quick responses for code snippets, explanations, and prototyping | Lower latency |
| o4-mini | Fast help with simple or repetitive tasks | Fast, reliable answers to lightweight coding questions | Lower latency |
| Claude Opus 4 | Deep reasoning and debugging | Advanced agentic workflows over large codebases, long-horizon projects | Reasoning |
| Claude Sonnet 3.5 | Fast help with simple or repetitive tasks | Quick responses for code, syntax, and documentation | Agent mode |
| Claude Sonnet 3.7 | Deep reasoning and debugging | Structured reasoning across large, complex codebases | Agent mode |
| Claude Sonnet 4 | Deep reasoning and debugging | High-performance code review, bug fixes, and efficient research workflows | Agent mode |
| Gemini 2.5 Pro | Deep reasoning and debugging | Complex code generation, debugging, and research workflows | Reasoning |
| Gemini 2.0 Flash | Working with visuals (diagrams, screenshots) | Real-time responses and visual reasoning for UI and diagram-based tasks | Visual |
Use these models for common development tasks that require a balance of quality, speed, and cost efficiency. These models are a good default when you don't have specific requirements.
| Model | Why it's a good fit |
|---|---|
| GPT-4.1 | Reliable default for most coding and writing tasks. Fast, accurate, and works well across languages and frameworks. |
| GPT-4o | Delivers GPT-4–level performance with lower latency. |
| Claude Sonnet 3.7 | Produces clear, structured output. Follows formatting instructions and maintains consistent style. |
| Gemini 2.0 Flash | Fast and cost-effective. Well suited for quick questions, short code snippets, and lightweight writing tasks. |
| o4-mini | Optimized for speed and cost efficiency. Ideal for real-time suggestions with low usage overhead. |
Use one of these models if you want to:
- Write or review functions, short files, or code diffs.
- Generate documentation, comments, or summaries.
- Explain errors or unexpected behavior quickly.
- Work in a non-English programming environment.
If you're working on complex refactoring, architectural decisions, or multi-step logic, consider a model from Deep reasoning and debugging. For faster, simpler tasks like repetitive edits or one-off code suggestions, see Fast help with simple or repetitive tasks.
These models are optimized for speed and responsiveness. They’re ideal for quick edits, utility functions, syntax help, and lightweight prototyping. You’ll get fast answers without waiting for unnecessary depth or long reasoning chains.
| Model | Why it's a good fit |
|---|---|
| o4-mini | A quick and cost-effective model for repetitive or simple coding tasks. Offers clear, concise suggestions. |
| o3-mini | Provides low-latency, accurate responses. Great for real-time suggestions and code walkthroughs. |
| Claude Sonnet 3.5 | Balances fast responses with quality output. Ideal for small tasks and lightweight code explanations. |
| Gemini 2.0 Flash | Extremely low latency and multimodal support (where available). Great for fast, interactive feedback. |
Use one of these models if you want to:
- Write or edit small functions or utility code.
- Ask quick syntax or language questions.
- ideas with minimal setup.
- Get fast feedback on simple prompts or edits.
If you’re working on complex refactoring, architectural decisions, or multi-step logic, see Deep reasoning and debugging. For tasks that need stronger general-purpose reasoning or more structured output, see General-purpose coding and writing.
These models are designed for tasks that require step-by-step reasoning, complex decision-making, or high-context awareness. They work well when you need structured analysis, thoughtful code generation, or multi-file understanding.
| Model | Why it's a good fit |
|---|---|
| GPT-4.5 | Delivers consistent results for multi-step logic, long-context tasks, and complex reasoning. Ideal for debugging and planning. |
| o3 | Strong at algorithm design, system debugging, and architecture decisions. Balances performance and reasoning. |
| o1 | Excels at deliberate, structured reasoning and deep analysis. Good for performance tuning and problem-solving. |
| Claude Sonnet 3.7 | Provides hybrid reasoning that adapts to both fast tasks and deeper thinking. |
| Claude Sonnet 4 | Improves on 3.7 with more reliable completions and smarter reasoning under pressure. |
| Claude Opus 4 | Anthropic’s most powerful model. Strong at strategy, debugging, and multi-layered logic. |
| Gemini 2.5 Pro | Advanced reasoning across long contexts and scientific or technical analysis. |
Use one of these models if you want to:
- Debug complex issues with context across multiple files.
- Refactor large or interconnected codebases.
- Plan features or architecture across layers.
- Weigh trade-offs between libraries, patterns, or workflows.
- Analyze logs, performance data, or system behavior.
For fast iteration or lightweight tasks, see Fast help with simple or repetitive tasks. For general development workflows or content generation, see General-purpose coding and writing.
Use these models when you want to ask questions about screenshots, diagrams, UI components, or other visual input. These models support multimodal input and are well suited for front-end work or visual debugging.
| Model | Why it's a good fit |
|---|---|
| GPT-4o | Supports image input. Great for interpreting screenshots or debugging UI issues with visual context. |
| Gemini 2.0 Flash | Fast, multimodal model optimized for real-time interaction. Useful for feedback on diagrams, visual s, and UI layouts. |
Use one of these models if you want to:
- Ask questions about diagrams, screenshots, or UI components.
- Get feedback on visual drafts or workflows.
- Understand front-end behavior from visual context.
Tip
If you're using a model in a context that doesn’t support image input (like a code editor), you won’t see visual reasoning benefits. You may be able to use an MCP server to get access to visual input indirectly. See Extending Copilot Chat with the Model Context Protocol (MCP).
If your task involves deep reasoning or large-scale refactoring, consider a model from Deep reasoning and debugging. For text-only tasks or simpler code edits, see Fast help with simple or repetitive tasks.
Choosing the right model helps you get the most out of Copilot. If you're not sure which model to use, start with a general-purpose option like GPT-4.1 or GPT-4o, then adjust based on your needs.
- For detailed model specs and pricing, see Supported AI models in Copilot.
- For more examples of how to use different models, see Comparing AI models using different tasks.
- To switch between models, refer to Changing the AI model for Copilot Chat or Changing the AI model for Copilot code completion.