You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 3b48681
Browse filesBrowse the repository at this point in the historyBrowse files
authored
Remove models retired on 2026-09-01 from availability docs (#62850)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Copilot-Session: cc37d0bd-c6d3-4849-83f9-f631f7b45eb2
Copilot-Session: a8e2667d-7f41-4341-b1ca-58c0a42d3a73
Copy file name to clipboardExpand all lines: content/copilot/concepts/agents/copilot-cli/fleet.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -29,7 +29,7 @@ When you use the `/fleet` command, the main {% data variables.product.prodname_c
29
29
30
30
***Specialization**: If you've defined custom agents that are specialized for certain types of work, these may be used by the subagents. This allows for specialization, with the subagents using the custom agents best suited to the specific subtask they are working on.
31
31
32
-
By default, subagents use a low-cost AI model. However, you can tell {% data variables.product.prodname_copilot_short %} to use a specific model for part of the work. For example, within a larger prompt, you could specify `... Use GPT-5.3-Codex, to create ... Use Claude Opus 4.5, to analyze ...`. If a subagent uses a custom agent profile that specifies a particular AI model, then that model will be used by the subagent. Using a specific model may produce better quality results for particular types of subtask.
32
+
By default, subagents use a low-cost AI model. However, you can tell {% data variables.product.prodname_copilot_short %} to use a specific model for part of the work. For example, within a larger prompt, you could specify `... Use GPT-5.3-Codex, to create ... Use Claude Opus 5, to analyze ...`. If a subagent uses a custom agent profile that specifies a particular AI model, then that model will be used by the subagent. Using a specific model may produce better quality results for particular types of subtask.
33
33
34
34
If custom agents are available, {% data variables.product.prodname_copilot_short %} will decide whether to use one to complete a particular subtask. However, if you know that a specific custom agent is well-suited to a particular subtask, you can specify this in your prompt by using `@CUSTOM-AGENT-NAME`. For example, within a larger prompt: `... Use @test-writer to create comprehensive unit tests for ...`.
Copy file name to clipboardExpand all lines: content/copilot/how-tos/copilot-cli/cli-best-practices.md
+6-6Lines changed: 6 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -87,15 +87,15 @@ Use `/model` to choose from available models based on your task complexity:
87
87
| Model | Best For | Tradeoffs |
88
88
| ----- | -------- | --------- |
89
89
|**Auto**| Reduced rate limiting and lower latency and errors | See [AUTOTITLE](/copilot/concepts/models/auto-model-selection)|
90
-
|**Claude Opus 4.5** (default)| Complex architecture, difficult debugging, nuanced refactoring | Most capable but more costly |
91
-
|**Claude Sonnet 4.5**| Day-to-day coding, most routine tasks | Fast, cost-effective, handles most work well |
92
-
|**GPT-5.2 Codex**| Code generation, code review, straightforward implementations | Excellent for reviewing code produced by other models |
90
+
|**{% data variables.copilot.copilot_claude_opus_5 %}**| Complex architecture, difficult debugging, nuanced refactoring | Most capable but more costly |
91
+
|**{% data variables.copilot.copilot_claude_sonnet_5 %}**| Day-to-day coding, most routine tasks | Fast, cost-effective, handles most work well |
92
+
|**{% data variables.copilot.copilot_gpt_53_codex %}**| Code generation, code review, straightforward implementations | Excellent for reviewing code produced by other models |
93
93
94
94
**Recommendations:**
95
95
96
96
***Auto** intelligently chooses models based on real-time system health and model performance (reducing rate limiting and providing lower latency and errors), and the complexity of the task you have given {% data variables.product.prodname_copilot_short %}.
97
-
***Opus 4.5** is ideal for tasks requiring deep reasoning, complex system design, subtle bug investigation, or extensive context understanding.
98
-
***Switch to Sonnet 4.5** for routine tasks where speed and cost efficiency matter—it handles the majority of everyday coding effectively.
97
+
***{% data variables.copilot.copilot_claude_opus_5 %}** is ideal for tasks requiring deep reasoning, complex system design, subtle bug investigation, or extensive context understanding.
98
+
***Switch to {% data variables.copilot.copilot_claude_sonnet_5 %}** for routine tasks where speed and cost efficiency matter—it handles the majority of everyday coding effectively.
99
99
***Use Codex** for high-volume code generation and as a second opinion for reviewing code produced by other models.
100
100
101
101
You can switch models mid-session with `/model` as task complexity changes.
@@ -336,7 +336,7 @@ Pair with {% data variables.copilot.copilot_cli_short %} to develop tests.
336
336
### Code review assistance
337
337
338
338
*``/security-review Review my current local changes for security issues. Prioritize high-severity findings and suggest remediations I can apply before opening a pull request.``
339
-
*``/review Use Opus 4.5 and Codex 5.2 to review the changes in my current branch against `main`. Focus on potential bugs and security issues.``
339
+
*``/review Use {% data variables.copilot.copilot_claude_opus_5 %} and {% data variables.copilot.copilot_gpt_53_codex %} to review the changes in my current branch against `main`. Focus on potential bugs and security issues.``
340
340
* Triage high-severity findings first, validate your fixes, then continue through your normal pull request review workflow.
Copy file name to clipboardExpand all lines: content/copilot/reference/ai-models/model-comparison.md
+3-6Lines changed: 3 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -40,7 +40,6 @@ Use these models for common development tasks that require a balance of quality,
40
40
| {% data variables.copilot.copilot_gpt_53_codex %} | Delivers higher-quality code on complex engineering tasks like features, tests, debugging, refactors, and reviews without lengthy instructions. |
41
41
| {% data variables.copilot.copilot_gpt_5_mini %} | Reliable default for most coding and writing tasks. Fast, accurate, and works well across languages and frameworks. |
42
42
| {% data variables.copilot.copilot_gpt_56_terra %} | Balanced all-round choice for everyday interactive and agentic coding. |
43
-
| {% data variables.copilot.copilot_raptor_mini %} | Specialized for fast, accurate inline suggestions and explanations. |
44
43
| {% data variables.copilot.copilot_mai_code_1_flash %} | Strong instruction-following and adaptive reasoning make it a reliable default for everyday coding tasks, writing, and multi-turn development workflows. |
45
44
46
45
### When to use these models
@@ -93,9 +92,8 @@ These models are designed for tasks that require step-by-step reasoning, complex
93
92
| {% data variables.copilot.copilot_gpt_5_mini %} | Delivers deep reasoning and debugging with faster responses and lower resource usage than GPT-5. Ideal for interactive sessions and step-by-step code analysis. |
94
93
| {% data variables.copilot.copilot_gpt_55 %} | Great at complex reasoning, code analysis, and technical decision-making. |
95
94
| {% data variables.copilot.copilot_gpt_56_sol %} | The highest reasoning ceiling in the GPT-5.6 family. Best for complex reasoning over large codebases and demanding, long-running agentic work. |
96
-
| {% data variables.copilot.copilot_claude_sonnet_46 %} | Improves on Sonnet 4.5 with more reliable completions and smarter reasoning under pressure. |
97
-
| {% data variables.copilot.copilot_claude_opus_47 %} | Anthropic’s most powerful model. Improves on {% data variables.copilot.copilot_claude_opus_46 %}. |
98
-
| {% data variables.copilot.copilot_gemini_31_pro %} | Advanced reasoning across long contexts and scientific or technical analysis. |
95
+
| {% data variables.copilot.copilot_claude_sonnet_46 %} | Reliable completions and smarter reasoning under pressure. |
96
+
| {% data variables.copilot.copilot_claude_opus_47 %} | Anthropic’s most powerful model. Strong at deep reasoning over large, complex codebases. |
99
97
100
98
### When to use these models
101
99
@@ -119,8 +117,7 @@ Use these models when you want to ask questions about screenshots, diagrams, UI
| {% data variables.copilot.copilot_gpt_5_mini %} | Reliable default for most coding and writing tasks. Fast, accurate, and supports multimodal input for visual reasoning tasks. Works well across languages and frameworks. |
122
-
| {% data variables.copilot.copilot_claude_sonnet_46 %} | Improves on Sonnet 4.5 with more reliable completions and smarter reasoning under pressure. |
123
-
| {% data variables.copilot.copilot_gemini_31_pro %} | Deep reasoning and debugging, ideal for complex code generation, debugging, and research workflows. |
120
+
| {% data variables.copilot.copilot_claude_sonnet_46 %} | Reliable completions and smarter reasoning under pressure. |
Copy file name to clipboardExpand all lines: content/copilot/reference/ai-models/model-hosting.md
-5Lines changed: 0 additions & 5 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -41,11 +41,8 @@ All input requests and output responses processed by {% data variables.product.p
41
41
Used for:
42
42
43
43
* {% data variables.copilot.copilot_claude_haiku_45 %}
44
-
* {% data variables.copilot.copilot_claude_sonnet_45 %}
45
44
* {% data variables.copilot.copilot_claude_sonnet_46 %}
46
45
* {% data variables.copilot.copilot_claude_sonnet_5 %}
47
-
* {% data variables.copilot.copilot_claude_opus_45 %}
48
-
* {% data variables.copilot.copilot_claude_opus_46 %}
49
46
* {% data variables.copilot.copilot_claude_opus_47 %}
50
47
* {% data variables.copilot.copilot_claude_opus_48 %}
51
48
* {% data variables.copilot.copilot_claude_opus_48_fast %}
@@ -80,7 +77,6 @@ When using {% data variables.copilot.copilot_claude %}, input prompts and output
80
77
81
78
Used for:
82
79
83
-
* {% data variables.copilot.copilot_gemini_31_pro %}
84
80
* {% data variables.copilot.copilot_gemini_35_flash %}
85
81
* {% data variables.copilot.copilot_gemini_36_flash %}
86
82
* {% data variables.copilot.copilot_gemini_37_flash %}
@@ -121,7 +117,6 @@ Used for:
121
117
122
118
* {% data variables.copilot.copilot_mai_code_1_flash %}
123
119
* {% data variables.copilot.copilot_mai_code_1_1_flash %}
124
-
* {% data variables.copilot.copilot_raptor_mini %}
125
120
126
121
{% data variables.copilot.copilot_mai_code_1_flash %} and {% data variables.copilot.copilot_mai_code_1_1_flash %} are first-party Microsoft models hosted on Azure in {% data variables.product.github %}'s tenant.
Copy file name to clipboardExpand all lines: content/copilot/reference/copilot-cli-reference/cli-programmatic-reference.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -39,7 +39,7 @@ There are a number of command-line options that are particularly useful when run
39
39
|`--allow-tool=TOOL ...`| Selectively grant permission for a specific tool. For multiple tools, use a quoted, comma-separated list. |
40
40
|`--allow-url=URL ...`| Allow the agent to fetch a specific URL or domain. Useful when a workflow needs web access to known endpoints. For multiple URLs, use a quoted, comma-separated list. |
41
41
|`--deny-tool=TOOL ...`| Deny a specific tool. Useful for restricting what the agent can do in a locked-down workflow. For multiple tools, use a quoted, comma-separated list. |
42
-
|`--model=MODEL`| Choose the AI model (for example, `gpt-5.2` or `claude-sonnet-4.6`). Useful for pinning a model in reproducible workflows. See [Choosing a model](#choosing-a-model) below. |
42
+
|`--model=MODEL`| Choose the AI model (for example, `gpt-5.4` or `claude-haiku-4.5`). Useful for pinning a model in reproducible workflows. See [Choosing a model](#choosing-a-model) below. |
43
43
|`--no-ask-user`| Prevent the agent from pausing to seek additional user input. |
44
44
|`--secret-env-vars=VAR ...`| An environment variable whose value you want redacted in output. For multiple variables, use a quoted, comma-separated list. Essential for preventing secrets being exposed in logs. The values in the `GITHUB_TOKEN` and `COPILOT_GITHUB_TOKEN` environment variables are redacted by default. |
45
45
|`--share=PATH`| Export the session transcript to a markdown file after non-interactive completion (defaults to `./copilot-session-<ID>.md`). Useful for auditing or archiving what the agent did. Note that session transcripts may contain sensitive information. |
@@ -86,7 +86,7 @@ You can use environment variables to configure various aspects of the CLI's beha
86
86
| Variable | Description |
87
87
| --------------------- | ------------- |
88
88
|`COPILOT_ALLOW_ALL`| Set to `true` for full permissions |
89
-
|`COPILOT_MODEL`| Set the model (for example, `gpt-5.2`, `claude-sonnet-4.5`) |
89
+
|`COPILOT_MODEL`| Set the model (for example, `gpt-5.4`, `claude-haiku-4.5`) |
90
90
|`COPILOT_HOME`| Set the directory for the CLI configuration file (`~/.copilot` by default) |
@@ -115,7 +115,7 @@ copilot -p "Fix the race condition in the worker pool" \
115
115
```
116
116
117
117
> [!NOTE]
118
-
> You can find the model strings for all available models in the description of the `--model`option when you enter `copilot help` in your terminal.
118
+
> To see the model strings for all available models, run the `/model`command in an interactive {% data variables.copilot.copilot_cli_short %} session. For the full list of models and the clients that support them, see [AUTOTITLE](/copilot/reference/ai-models/supported-models).
119
119
120
120
Alternatively, you can set the `COPILOT_MODEL` environment variable to specify a model for the duration of the shell session.
Copy file name to clipboardExpand all lines: content/copilot/tutorials/compare-ai-models.md
-15Lines changed: 0 additions & 15 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -190,21 +190,6 @@ For a complete walkthrough of the scenario, see [AUTOTITLE](/copilot/tutorials/w
190
190
* It performs well on everyday coding tasks like test generation, boilerplate scaffolding, and validation logic.
191
191
* The task leans into multi-step reasoning, but still stays within the confidence zone of a less advanced model because the logic isn’t too deep.
192
192
193
-
## {% data variables.copilot.copilot_claude_sonnet_45 %}
194
-
195
-
{% data reusables.copilot.model-use-cases.claude-sonnet-45 %}
196
-
197
-
### Example scenario
198
-
199
-
Consider a scenario where you're modernizing a legacy COBOL application by rewriting it in Node.js. The project involves understanding unfamiliar source code, converting logic across languages, iteratively building the replacement, and verifying correctness through a test suite.
200
-
201
-
For a complete walkthrough of the scenario, see [AUTOTITLE](/copilot/tutorials/modernize-legacy-code).
202
-
203
-
### Why {% data variables.copilot.copilot_claude_sonnet_45 %} is a good fit
204
-
205
-
* {% data variables.copilot.copilot_claude_sonnet_45 %} handles complex context well, making it suited for workflows that span multiple files or languages.
206
-
* Its hybrid reasoning architecture allows it to switch between quick answers and deeper, step-by-step problem-solving.
Copy file name to clipboardExpand all lines: content/copilot/tutorials/vibe-coding.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -71,9 +71,9 @@ We'll create a time-tracking app in a new {% data variables.product.github %} re
71
71
1. Choose a model from the models dropdown.
72
72
73
73
> [!NOTE]
74
-
> The responses referred to in this tutorial were received while using Claude Sonnet 4.5. Other models will respond differently, but you should get roughly similar results. Claude Sonnet 4.5 is a good choice, if it's available, as it provides useful commentary in the chat view, explaining what it is doing, and giving detailed summaries when it has finished coding.
74
+
> The responses referred to in this tutorial were received while using {% data variables.copilot.copilot_claude_sonnet_45 %}, which has since been retired. Other models will respond differently, but you should get roughly similar results.
75
75
>
76
-
> If Claude Sonnet 4.5 is not available, set the model to **Auto** or select a model of your choice.
76
+
> Set the model to **Auto**, or select a model of your choice.
0 commit comments