Answer: You can select a model and reasoning effort from the dropdowns below the prompt field, and you can change both settings at any time during a session. Hover over the icon in the model picker to see model details. Status: Confirmed Entry: tool/github-copilot/models/choose-session-model Revision: 3 Digest: sha256:e764cfdb5edf9cb4 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:29:34Z Last changed: 2026-11-18T13:05:37Z (Fusion option: — → Fusion) Last verified: 2026-11-20T13:10:13Z Next check: 2026-11-21T13:10:13Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Model selection location | dropdowns below the prompt field | [1] | 2026-11-20 Reasoning effort effect | Higher reasoning effort gives the agent more time to think through complex problems but may take longer | [1] | 2026-11-20 Changing settings | at any time during a session | [1] | 2026-11-20 Fusion option | Fusion | [1] | 2026-11-20 Model details | Hover over the icon in the model picker to see model details | [1] | 2026-11-20 Sources: [1] GitHub. "Working with agent sessions in the GitHub Copilot app - GitHub Docs". https://docs.github.com/en/copilot/how-tos/github-copilot-app/agent-sessions Role: primary. Accessed: 2026-11-20T13:10:13Z Quote: "You can select a model and reasoning effort from the dropdowns below the prompt field." (Supports: Model selection location) Quote: "Higher reasoning effort gives the agent more time to think through complex problems but may take longer." (Supports: Reasoning effort effect) Quote: "You can change both settings at any time during a session." (Supports: Changing settings) Quote: "If you choose Fusion in the model picker and then an effort level, the app automatically selects the models and execution patterns for your task." (Supports: Fusion option) Quote: "Hover over the icon in the model picker to see model details." (Supports: Model details) Snapshot SHA-256: 62c3f7221f640a8decd76d3f71074b74de31eb591099ae86a9085b62650e206b (captured 2026-11-18T13:05:38Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-18T13:05:37Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T13:10:13Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:10:13Z Last attempt: 2026-11-20T13:10:13Z Notes and limitations: Extracted automatically from a single official source (section "Choosing a model"). Related: https://latestn.com/tool/github-copilot/models/cloud-agent-reasoning-level What is the reasoning level setting for the GitHub Copilot cloud agent and how does it work? https://latestn.com/tool/github-copilot/models/cloud-agent-supported-models Which AI models can I use with the GitHub Copilot cloud agent? https://latestn.com/tool/github-copilot/models/configure-ai-model-access How do I configure which AI models are available in GitHub Copilot? https://latestn.com/tool/github-copilot/models/choose-model-linear How do I choose which model GitHub Copilot cloud agent uses in Linear? https://latestn.com/tool/github-copilot/models/choose-model-or-custom-agent How do I choose a model or a custom agent in GitHub Copilot agent mode? https://latestn.com/tool/github-copilot/models/choose-right-model-for-task How do I choose the right model for a task in GitHub Copilot to reduce cost? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-18T13:05:37Z | changed | Fusion option: — → Fusion | [1] 2026-11-18T13:05:37Z | changed | Changing settings: — → at any time during a session | [1] 2026-11-18T13:05:37Z | changed | Reasoning effort effect: — → Higher reasoning effort gives the agent more time to think through complex problems but may take longer | [1] 2026-11-18T13:05:37Z | changed | Model selection location: — → dropdowns below the prompt field | [1] 2026-11-18T13:05:37Z | changed | Custom provider models: those models also appear in the picker → — | [1] 2026-11-18T13:05:37Z | changed | Fusion behavior: the app automatically selects the models and execution patterns for your task → — | [1] 2026-11-18T13:05:37Z | changed | Model details: Hover over the icon in the model picker → Hover over the icon in the model picker to see model details | [1] 2026-11-18T13:05:37Z | changed | When settings can be changed: at any time during a session → — | [1] 2026-11-18T13:05:37Z | changed | Where to select model: dropdowns below the prompt field → — | [1] 2026-11-16T12:54:18Z | changed | Custom provider models: — → those models also appear in the picker | [1] 2026-11-16T12:54:18Z | changed | Fusion behavior: — → the app automatically selects the models and execution patterns for your task | [1] 2026-11-16T12:54:18Z | changed | When settings can be changed: — → at any time during a session | [1] 2026-11-16T12:54:18Z | changed | Where to select model: — → dropdowns below the prompt field | [1] 2026-11-16T12:54:18Z | changed | Custom model provider: If you configured your own model provider in the app, those models also appear in the picker. → — | [1] 2026-11-16T12:54:18Z | changed | Fusion option: If you choose Fusion in the model picker and then an effort level, the app automatically selects the models and execution patterns for your task. → — | [1] 2026-11-16T12:54:18Z | changed | Model details: Hover over the icon in the model picker to see model details. → Hover over the icon in the model picker | [1] 2026-11-16T12:54:18Z | changed | Changing settings: change both settings at any time during a session → — | [1] 2026-11-16T12:54:18Z | changed | How to select a model: select a model and reasoning effort from the dropdowns below the prompt field → — | [1] 2026-11-13T03:29:34Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/github-copilot/models/choose-session-model/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/github-copilot/models/choose-session-model POST: https://latestn.com/dispute/tool/github-copilot/models/choose-session-model with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/github-copilot/models/choose-session-model?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I choose a model for an agent session in the GitHub Copilot app? Revision 3, last verified 2026-11-20T13:10:13Z. https://latestn.com/tool/github-copilot/models/choose-session-model (accessed 2026-11-21T09:52:26Z). @misc{LatestN_tool_github_copilot_models_choose_session_model_r3, title = {How do I choose a model for an agent session in the GitHub Copilot app?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/github-copilot/models/choose-session-model}}, note = {Revision 3; digest sha256:e764cfdb5edf9cb4; last verified 2026-11-20T13:10:13Z; accessed 2026-11-21T09:52:26Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/github-copilot/models/choose-session-model