Skip to content

Commit af88f96

Browse files
sunbryesunbrye
authored
Tented [4-14] (#55267)
1 parent 47785d5 commit af88f96

File tree

8 files changed

+46
-8
lines changed

8 files changed

+46
-8
lines changed

‎content/copilot/managing-copilot/managing-copilot-for-your-enterprise/managing-policies-and-features-for-copilot-in-your-enterprise.md

Lines changed: 1 addition & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -92,10 +92,7 @@ By default, {% data variables.product.prodname_copilot_chat_short %} uses a base
9292

9393
* **{% data variables.copilot.copilot_claude_sonnet %}**. See [AUTOTITLE](/copilot/using-github-copilot/ai-models/using-claude-sonnet-in-github-copilot).
9494
* **{% data variables.copilot.copilot_gemini %}**. See [AUTOTITLE](/copilot/using-github-copilot/ai-models/using-gemini-in-github-copilot).
95-
* **OpenAI's models:**
96-
* **o1**: This model is focused on advanced reasoning and solving complex problems, in particular in math and science. It responds more slowly than the GPT-4o model. Each member of your enterprise can make 10 requests to this model per day.
97-
* **o3-mini**: This is the next generation of reasoning models, following from o1 and o1-mini. The o3-mini model outperforms o1 on coding benchmarks with response times that are comparable to o1-mini, providing improved quality at nearly the same latency. It is best suited for code generation and small context operations. Each member of your enterprise can make 50 requests to this model every 12 hours. {% ifversion copilot-enterprise %}
98-
* **GPT-4.5**: This model is designed with advanced capabilities in intuition, writing style, and broad knowledge. It performs effectively with creative prompts and provides reliable responses to obscure knowledge queries. Each member of your enterprise can make 10 requests to this model every 12 hours. {% endif %}
95+
* **OpenAI's models:** See [AUTOTITLE](/copilot/using-github-copilot/ai-models/choosing-the-right-ai-model-for-your-task#gpt-45).
9996

10097
### {% data variables.product.prodname_copilot_short %} Metrics API access
10198

‎content/copilot/managing-copilot/managing-github-copilot-in-your-organization/managing-policies-for-copilot-in-your-organization.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -38,7 +38,7 @@ Organization owners can set policies to govern how {% data variables.product.pro
3838
* Access to alternative models for {% data variables.product.prodname_copilot_short %}
3939
* Anthropic {% data variables.copilot.copilot_claude_sonnet %} in {% data variables.product.prodname_copilot_short %}
4040
* Google {% data variables.copilot.copilot_gemini %} in {% data variables.product.prodname_copilot_short %}
41-
* OpenAI o1 and o3 models in {% data variables.product.prodname_copilot_short %}
41+
* OpenAI models in {% data variables.product.prodname_copilot_short %}
4242

4343
The policy settings selected by an organization owner determine the behavior of {% data variables.product.prodname_copilot %} for all organization members that have been granted access to {% data variables.product.prodname_copilot_short %} through the organization.
4444

‎content/copilot/managing-copilot/monitoring-usage-and-entitlements/about-premium-requests.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -47,6 +47,7 @@ Each model has a premium request multiplier, based on its complexity and resourc
4747
| {% data variables.copilot.copilot_claude_sonnet_37 %} Thinking | 1.25 |
4848
| {% data variables.copilot.copilot_gemini_flash %} | 0.25 |
4949
| {% data variables.copilot.copilot_gemini_25_pro %} | 1 |
50+
| {% data variables.copilot.copilot_gpt_41 %} | 1 |
5051
| GPT-4.5 | 50 |
5152
| o1 | 10 |
5253
| o3-mini | 0.33 |

‎content/copilot/using-github-copilot/ai-models/changing-the-ai-model-for-copilot-chat.md

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -27,7 +27,8 @@ However, you are not limited to using this model. You can choose from a selectio
2727

2828
The following models are currently available in the immersive mode of {% data variables.product.prodname_copilot_chat_short %}:
2929

30-
* {% data variables.copilot.copilot_gpt_4o %} {% ifversion copilot-enterprise %}
30+
* {% data variables.copilot.copilot_gpt_4o %}
31+
* {% data variables.copilot.copilot_gpt_41 %} {% ifversion copilot-enterprise %}
3132
* {% data variables.copilot.copilot_gpt_45 %} {% endif %}
3233
* {% data variables.copilot.copilot_claude_sonnet_35 %}
3334
* {% data variables.copilot.copilot_claude_sonnet_37 %}
@@ -73,7 +74,8 @@ Changing the model that's used by {% data variables.product.prodname_copilot_cha
7374

7475
The following models are currently available through multi-model {% data variables.product.prodname_copilot_chat_short %}:
7576

76-
* {% data variables.copilot.copilot_gpt_4o %} {% ifversion copilot-enterprise %}
77+
* {% data variables.copilot.copilot_gpt_4o %}
78+
* {% data variables.copilot.copilot_gpt_41 %} {% ifversion copilot-enterprise %}
7779
* {% data variables.copilot.copilot_gpt_45 %} {% endif %}
7880
* {% data variables.copilot.copilot_claude_sonnet_35 %}
7981
* {% data variables.copilot.copilot_claude_sonnet_37 %}

‎content/copilot/using-github-copilot/ai-models/choosing-the-right-ai-model-for-your-task.md

Lines changed: 36 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -16,13 +16,14 @@ This article helps you compare the available models, understand the strengths of
1616

1717
The best model depends on your use case:
1818

19-
* For **balance between cost and performance**, try GPT-4o or {% data variables.copilot.copilot_claude_sonnet_35 %}.
19+
* For **balance between cost and performance**, try {% data variables.copilot.copilot_gpt_41 %} or {% data variables.copilot.copilot_claude_sonnet_37 %}.
2020
* For **fast, low-cost support for basic tasks**, try o3-mini or {% data variables.copilot.copilot_claude_sonnet_35 %}.
2121
* For **deep reasoning or complex coding challenges**, try o1, GPT-4.5, or {% data variables.copilot.copilot_claude_sonnet_37 %}.
2222
* For **multimodal inputs and real-time performance**, try {% data variables.copilot.copilot_gemini_flash %} or GPT-4o.
2323

2424
You can click a model name in the list below to jump to a detailed overview of its strengths and use cases.
2525
* [GPT-4o](#gpt-4o)
26+
* [{% data variables.copilot.copilot_gpt_41 %}](#gpt-41)
2627
* [GPT-4.5](#gpt-45)
2728
* [o1](#o1)
2829
* [o3-mini](#o3-mini)
@@ -75,6 +76,40 @@ The following table summarizes when an alternative model may be a better choice:
7576

7677
{% endrowheaders %}
7778

79+
## {% data variables.copilot.copilot_gpt_41 %}
80+
81+
OpenAI’s latest model, {% data variables.copilot.copilot_gpt_41 %}, is now available in {% data variables.product.prodname_copilot %} and {% data variables.product.prodname_github_models %}, bringing OpenAI’s newest model to your coding workflow. This model outperforms GPT-4o across the board, with major gains in coding, instruction following, and long-context understanding. It has a larger context window and features a refreshed knowledge cutoff of June 2024.
82+
83+
OpenAI has optimized {% data variables.copilot.copilot_gpt_41 %} for real-world use based on direct developer feedback about: frontend coding, making fewer extraneous edits, following formats reliably, adhering to response structure and ordering, consistent tool usage, and more. This model is a strong default choice for common development tasks that benefit from speed, responsiveness, and general-purpose reasoning.
84+
85+
### Use cases
86+
87+
{% data reusables.copilot.model-use-cases.gpt-41 %}
88+
89+
### Strengths
90+
91+
The following table summarizes the strengths of {% data variables.copilot.copilot_gpt_41 %}:
92+
93+
{% rowheaders %}
94+
95+
| Task | Description | Why {% data variables.copilot.copilot_gpt_41 %} is a good fit |
96+
|-----------------------------------|---------------------------------------------------------------------|-----------------------------------------------------------------|
97+
| Code explanation | Understand what a block of code does or walk through logic. | Fast and accurate explanations. |
98+
| Code commenting and documentation | Generate or refine comments and documentation. | Writes clear, concise explanations. |
99+
| Bug investigation | Get a quick explanation or suggestion for an error. | Provides fast diagnostic insight. |
100+
| Code snippet generation | Generate small, reusable pieces of code. | Delivers high-quality results quickly. |
101+
| Multilingual prompts | Work with non-English prompts or identifiers. | Improved multilingual comprehension. |
102+
103+
{% endrowheaders %}
104+
105+
### Alternative options
106+
107+
| Task | Description | Why another model may be better |
108+
|------------------------------------|-------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------|
109+
| Multi-step reasoning or algorithms | Design complex logic or break down multi-step problems. | GPT-4.5 or {% data variables.copilot.copilot_claude_sonnet_37 %} provide better step-by-step thinking. |
110+
| Complex refactoring | Refactor large codebases or update multiple interdependent files. | GPT-4.5 handles context and code dependencies more robustly. |
111+
| System review or architecture | Analyze structure, patterns, or architectural decisions in depth. | {% data variables.copilot.copilot_claude_sonnet_37 %} or GPT-4.5 offer deeper analysis. |
112+
78113
## GPT-4.5
79114

80115
OpenAI GPT-4.5 improves reasoning, reliability, and contextual understanding. It works well for development tasks that involve complex logic, high-quality code generation, or interpreting nuanced intent.

‎data/reusables/copilot/differences-cfi-cfb-table.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -49,6 +49,7 @@
4949
| {% data variables.copilot.copilot_gemini_flash %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} |
5050
| {% data variables.copilot.copilot_gemini_25_pro %} | {% octicon "x" aria-label="Not included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} |
5151
| GPT-4o | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} |
52+
| {% data variables.copilot.copilot_gpt_41 %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} |
5253
| GPT-4.5 | {% octicon "x" aria-label="Not included" %} | {% octicon "x" aria-label="Not included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "x" aria-label="Not included" %} | {% octicon "check" aria-label="Included" %} |
5354
| o1 | {% octicon "x" aria-label="Not included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} |
5455
| o3-mini | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} | {% octicon "check" aria-label="Included" %} |

‎data/reusables/copilot/model-use-cases/gpt-41.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{% data variables.copilot.copilot_gpt_41 %} is a revamped version of OpenAI's GPT-4o model. This model is a strong default choice for common development tasks that benefit from speed, responsiveness, and general-purpose reasoning. If you're working on tasks that require broad knowledge, fast iteration, or basic code understanding, {% data variables.copilot.copilot_gpt_41 %} makes large improvements over GPT-4o.

‎data/variables/copilot.yml

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -46,6 +46,7 @@ copilot_gemini_flash: 'Gemini 2.0 Flash'
4646
copilot_gemini_25_pro: 'Gemini 2.5 Pro'
4747

4848
copilot_gpt_4o: 'GPT-4o'
49+
copilot_gpt_41: 'GPT-4.1'
4950
copilot_gpt_45: 'GPT-4.5'
5051
copilot_gpt_o1: 'o1'
5152
copilot_gpt_o3_mini: 'o3-mini'

0 commit comments

Comments
 (0)