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
| {% data variables.copilot.copilot_gpt_41 %} | 0 | 1 |
94
94
| {% data variables.copilot.copilot_gpt_4o %} | 0 | 1 |
95
-
| {% data variables.copilot.copilot_gpt_45 %} | 50 | Not applicable |
96
95
| {% data variables.copilot.copilot_claude_sonnet_35 %} | 1 | 1 |
97
96
| {% data variables.copilot.copilot_claude_sonnet_37 %} | 1 | Not applicable |
98
97
| {% data variables.copilot.copilot_claude_sonnet_37 %} Thinking | 1.25 | Not applicable |
99
98
| {% data variables.copilot.copilot_claude_sonnet_40 %} | 1 | Not applicable |
100
99
| {% data variables.copilot.copilot_claude_opus %} | 10 | Not applicable |
101
100
| {% data variables.copilot.copilot_gemini_flash %} | 0.25 | 1 |
102
101
| {% data variables.copilot.copilot_gemini_25_pro %} | 1 | Not applicable |
103
-
| {% data variables.copilot.copilot_o1 %} | 10 | Not applicable |
104
102
| {% data variables.copilot.copilot_o3 %} | 1 | Not applicable |
105
103
| {% data variables.copilot.copilot_o3_mini %} | 0.33 | 1 |
106
104
| {% data variables.copilot.copilot_o4_mini %} | 0.33 | Not applicable |
@@ -111,6 +109,6 @@ If you use **{% data variables.copilot.copilot_free_short %}**, you have access
111
109
112
110
Premium request usage is based on the model’s multiplier and the feature you’re using. For example:
113
111
114
-
***Using {% data variables.copilot.copilot_gpt_45 %} in {% data variables.copilot.copilot_chat_short %}**: With a 50× multiplier, one interaction counts as 50 premium requests.
112
+
***Using {% data variables.copilot.copilot_claude_opus %} in {% data variables.copilot.copilot_chat_short %}**: With a 10× multiplier, one interaction counts as 10 premium requests.
115
113
***Using {% data variables.copilot.copilot_gpt_41 %} on {% data variables.copilot.copilot_free_short %}**: Each interaction counts as 1 premium request.
116
114
***Using {% data variables.copilot.copilot_gpt_41 %} on a paid plan**: No premium requests are consumed.
Copy file name to clipboardExpand all lines: content/copilot/get-started/choosing-your-enterprises-plan-for-github-copilot.md
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -63,7 +63,7 @@ With {% data variables.copilot.copilot_code-review_short %}, {% data variables.p
63
63
64
64
{% data reusables.copilot.premium-requests-for-enterprises %}
65
65
66
-
To decide if you will benefit from a higher allowance for premium requests, compare the goals of your rollout to **development tasks** that each model is specialized in. For example, the o1 model is focused on math and science. Teams who work in specialized areas may require more requests to premium models. To learn about the benefits of different models, see [AUTOTITLE](/copilot/using-github-copilot/ai-models/choosing-the-right-ai-model-for-your-task).
66
+
To decide if you will benefit from a higher allowance for premium requests, compare the goals of your rollout to **development tasks** that each model is specialized in. For example, the {% data variables.copilot.copilot_claude_sonnet_40 %} is designed for advanced reasoning and coding tasks. Teams who work in specialized areas may require more requests to premium models. To learn about the benefits of different models, see [AUTOTITLE](/copilot/using-github-copilot/ai-models/choosing-the-right-ai-model-for-your-task).
67
67
68
68
Regardless of your plan, you can set a spending limit for premium requests over your plan's allowance. Premium requests over the allowance will be charged at a rate of {% data variables.copilot.additional_premium_requests %} per request, with an additional multiplier applied to certain models.
Copy file name to clipboardExpand all lines: content/copilot/how-tos/administer/enterprises/managing-policies-and-features-for-copilot-in-your-enterprise.md
+1-3Lines changed: 1 addition & 3 deletions
Original file line number
Diff line number
Diff line change
@@ -49,7 +49,7 @@ You can enable "{% data variables.product.prodname_copilot_short %} in {% data v
49
49
***{% data variables.product.prodname_copilot_short %} pull request summaries** - {% data variables.product.prodname_copilot_short %} can generate a summary of the changes made in a pull request, as well as a list of impacted files, using natural language. This overview helps reviewers quickly understand the proposed changes.
50
50
***{% data variables.product.prodname_copilot_short %} knowledge bases** - Organization owners can create knowledge bases consisting of Markdown documentation across one or more repositories, allowing organization members to use that documentation as context when they ask questions in {% data variables.copilot.copilot_chat_dotcom_short %}, {% data variables.copilot.copilot_chat_short %} in {% data variables.product.prodname_vscode %}, and {% data variables.copilot.copilot_chat_short %} in {% data variables.product.prodname_vs %}.
51
51
52
-
If you enable "{% data variables.product.prodname_copilot_short %} in {% data variables.product.prodname_dotcom_the_website %}", you can also configure additional features:
52
+
If you enable "{% data variables.product.prodname_copilot_short %} in {% data variables.product.prodname_dotcom_the_website %}," you can also configure additional features:
53
53
54
54
{% data reusables.copilot.policies-for-dotcom %}
55
55
@@ -87,8 +87,6 @@ Some features of {% data variables.product.prodname_copilot_short %} are availab
87
87
88
88
### {% data variables.product.prodname_copilot_short %} access to alternative AI models
89
89
90
-
> [!NOTE] Support for GPT-4.5 is only available on {% data variables.copilot.copilot_enterprise_short %}.
91
-
92
90
By default, {% data variables.copilot.copilot_chat_short %} uses an included model. If you grant access to the alternative models, members of your enterprise can choose to use these models rather than the included model. The available alternative models are:
93
91
94
92
***{% data variables.copilot.copilot_claude %}**. See [AUTOTITLE](/copilot/using-github-copilot/ai-models/using-claude-in-github-copilot).
Copy file name to clipboardExpand all lines: content/copilot/how-tos/troubleshoot/troubleshooting-common-issues-with-github-copilot.md
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -66,7 +66,7 @@ For more information, see the [{% data variables.copilot.copilot_cli_short %} ex
66
66
67
67
This error suggests that you have exceeded the rate limit for {% data variables.product.prodname_copilot_short %} requests. {% data variables.product.github %} uses rate limits to ensure everyone has fair access to the {% data variables.product.prodname_copilot_short %} service and to protect against abuse.
68
68
69
-
Most people see rate limiting for preview models, like OpenAI’s o1 and o3-mini, which are rate-limited due to limited capacity.
69
+
Most people see rate limiting for preview models, like OpenAI’s {% data variables.copilot.copilot_o3 %} and {% data variables.copilot.copilot_o4_mini %}, which are rate-limited due to limited capacity.
70
70
71
71
Service-level request rate limits ensure high service quality for all {% data variables.product.prodname_copilot_short %} users and should not affect typical or even deeply engaged {% data variables.product.prodname_copilot_short %} usage. We are aware of some use cases that are affected by it. {% data variables.product.github %} is iterating on {% data variables.product.prodname_copilot_short %}’s rate-limiting heuristics to ensure it doesn’t block legitimate use cases.
| {% data variables.copilot.copilot_gpt_41 %} | General-purpose coding and writing | Fast, accurate code completions and explanations | Agent mode, visual |
26
-
| {% data variables.copilot.copilot_gpt_45 %} | Deep reasoning and debugging | Multi-step reasoning and complex code generation | Reasoning |
27
26
| {% data variables.copilot.copilot_gpt_4o %} | General-purpose coding and writing | Fast completions and visual input understanding | Agent mode, visual |
28
-
| {% data variables.copilot.copilot_o1 %} | Deep reasoning and debugging | Step-by-step problem solving and deep logic analysis | Reasoning |
29
27
| {% data variables.copilot.copilot_o3 %} | Deep reasoning and debugging | Multi-step problem solving and architecture-level code analysis | Reasoning |
30
28
| {% data variables.copilot.copilot_o3_mini %} | Fast help with simple or repetitive tasks | Quick responses for code snippets, explanations, and prototyping | Lower latency |
31
29
| {% data variables.copilot.copilot_o4_mini %} | Fast help with simple or repetitive tasks | Fast, reliable answers to lightweight coding questions | Lower latency |
@@ -96,9 +94,7 @@ These models are designed for tasks that require step-by-step reasoning, complex
96
94
97
95
| Model | Why it's a good fit |
98
96
|-------|---------------------|
99
-
| {% data variables.copilot.copilot_gpt_45 %} | Delivers consistent results for multi-step logic, long-context tasks, and complex reasoning. Ideal for debugging and planning. |
100
97
| {% data variables.copilot.copilot_o3 %} | Strong at algorithm design, system debugging, and architecture decisions. Balances performance and reasoning. |
101
-
| {% data variables.copilot.copilot_o1 %} | Excels at deliberate, structured reasoning and deep analysis. Good for performance tuning and problem-solving. |
102
98
| {% data variables.copilot.copilot_claude_sonnet_37 %} | Provides hybrid reasoning that adapts to both fast tasks and deeper thinking. |
103
99
| {% data variables.copilot.copilot_claude_sonnet_40 %} | Improves on 3.7 with more reliable completions and smarter reasoning under pressure. |
104
100
| {% data variables.copilot.copilot_claude_opus %} | Anthropic’s most powerful model. Strong at strategy, debugging, and multi-layered logic. |
OpenAI {% data variables.copilot.copilot_o3_mini %} is a fast, cost-effective reasoning model designed to deliver coding performance while maintaining lower latency and resource usage. {% data variables.copilot.copilot_o3_mini %} outperforms {% data variables.copilot.copilot_o1 %} on coding benchmarks with response times that are comparable to o1-mini. {% data variables.product.prodname_copilot_short %} is configured to use OpenAI's "medium" reasoning effort.
80
+
OpenAI {% data variables.copilot.copilot_o3_mini %} is a fast, cost-effective reasoning model designed to deliver coding performance while maintaining lower latency and resource usage. {% data variables.product.prodname_copilot_short %} is configured to use OpenAI's "medium" reasoning effort.
Copy file name to clipboardExpand all lines: data/reusables/copilot/available-models-per-plan.md
-2Lines changed: 0 additions & 2 deletions
Original file line number
Diff line number
Diff line change
@@ -3,9 +3,7 @@
3
3
| Available models in chat | {% data variables.copilot.copilot_free_short %} | {% data variables.copilot.copilot_pro_short %} | {% data variables.copilot.copilot_pro_plus_short %} | {% data variables.copilot.copilot_business_short %} | {% data variables.copilot.copilot_enterprise_short %} |
0 commit comments