Skip to content

Commit 7a6596e

Browse files
sunbryejc-clark
sunbrye
and
jc-clark
authored
Deprecating 8 low-usage Copilot models [GA] (#58053)
Co-authored-by: Joe Clark <[email protected]>
1 parent 9d637ff commit 7a6596e

21 files changed

+638
-117
lines changed

‎content/copilot/concepts/billing/copilot-requests.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -93,14 +93,14 @@ Each model has a premium request multiplier, based on its complexity and resourc
9393

9494
{% data variables.copilot.copilot_gpt_5_mini %}, {% data variables.copilot.copilot_gpt_41 %} and {% data variables.copilot.copilot_gpt_4o %} are the included models, and do not consume any premium requests if you are on a **paid plan**.
9595

96-
If you use **{% data variables.copilot.copilot_free_short %}**, you have access to a limited number of models, and each model will consume one premium request when used. For example, if you make a request using the {% data variables.copilot.copilot_gemini_flash %} model, your interaction will consume **one premium request**, not 0.25 premium requests.
96+
If you use **{% data variables.copilot.copilot_free_short %}**, you have access to a limited number of models, and each model will consume one premium request when used.
9797

9898
{% data reusables.copilot.model-multipliers %}
9999

100100
## Examples of premium request usage
101101

102102
Premium request usage is based on the model’s multiplier and the feature you’re using. For example:
103103

104-
* **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.
104+
* **Using {% data variables.copilot.copilot_claude_opus_41 %} in {% data variables.copilot.copilot_chat_short %}**: With a 10× multiplier, one interaction counts as 10 premium requests.
105105
* **Using {% data variables.copilot.copilot_gpt_5_mini %} on {% data variables.copilot.copilot_free_short %}**: Each interaction counts as 1 premium request.
106106
* **Using {% data variables.copilot.copilot_gpt_5_mini %} on a paid plan**: No premium requests are consumed.

‎content/copilot/how-tos/troubleshoot-copilot/troubleshoot-common-issues.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -67,7 +67,7 @@ This is a known issue and our team is working towards a fix. For more informatio
6767

6868
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.
6969

70-
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+
Most people see rate limiting for preview models, due to limited capacity.
7171

7272
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.
7373

‎content/copilot/reference/ai-models/model-comparison.md‎

Lines changed: 0 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -33,17 +33,12 @@ Use this table to find a suitable model quickly, see more detail in the sections
3333
| {% data variables.copilot.copilot_gpt_5_codex %} | General-purpose coding and writing | Fast, accurate code completions and explanations | Agent mode | [{% data variables.copilot.copilot_gpt_5_codex %} model card](https://cdn.openai.com/pdf/97cc5669-7a25-4e63-b15f-5fd5bdc4d149/gpt-5-codex-system-card.pdf) |
3434
| {% data variables.copilot.copilot_gpt_5_mini %} | General-purpose coding and writing | Fast, accurate code completions and explanations | Agent mode, reasoning, vision | [{% data variables.copilot.copilot_gpt_5_mini %} model card](https://cdn.openai.com/gpt-5-system-card.pdf) |
3535
| {% data variables.copilot.copilot_gpt_5 %} | Deep reasoning and debugging | Multi-step problem solving and architecture-level code analysis | Reasoning | [{% data variables.copilot.copilot_gpt_5 %} model card](https://cdn.openai.com/gpt-5-system-card.pdf) |
36-
| {% data variables.copilot.copilot_o3 %} | Deep reasoning and debugging | Multi-step problem solving and architecture-level code analysis | Reasoning | [{% data variables.copilot.copilot_o3 %} model card](https://openai.com/index/o3-o4-mini-system-card/) |
37-
| {% data variables.copilot.copilot_o4_mini %} | Fast help with simple or repetitive tasks | Fast, reliable answers to lightweight coding questions | Lower latency | [{% data variables.copilot.copilot_o4_mini %} model card](https://openai.com/index/o3-o4-mini-system-card/) |
3836
| {% data variables.copilot.copilot_claude_haiku_45 %} | Fast help with simple or repetitive tasks | Fast, reliable answers to lightweight coding questions | Agent mode | Not available |
3937
| {% data variables.copilot.copilot_claude_sonnet_45 %} | General-purpose coding and agent tasks | Complex problem-solving challenges, sophisticated reasoning | Agent mode | [{% data variables.copilot.copilot_claude_sonnet_45 %} model card](https://assets.anthropic.com/m/12f214efcc2f457a/original/Claude-Sonnet-4-5-System-Card.pdf) |
4038
| {% data variables.copilot.copilot_claude_opus_41 %} | Deep reasoning and debugging | Complex problem-solving challenges, sophisticated reasoning | Reasoning, vision | [{% data variables.copilot.copilot_claude_opus_41 %} model card](https://assets.anthropic.com/m/4c024b86c698d3d4/original/Claude-4-1-System-Card.pdf) |
41-
| {% data variables.copilot.copilot_claude_opus %} | Deep reasoning and debugging | Complex problem-solving challenges, sophisticated reasoning | Reasoning, vision | [{% data variables.copilot.copilot_claude_opus %} model card](https://www-cdn.anthropic.com/6be99a52cb68eb70eb9572b4cafad13df32ed995.pdf) |
4239
| {% data variables.copilot.copilot_claude_sonnet_35 %} | Fast help with simple or repetitive tasks | Quick responses for code, syntax, and documentation | Agent mode, vision | [{% data variables.copilot.copilot_claude_sonnet_35 %} model card](https://www-cdn.anthropic.com/fed9cc193a14b84131812372d8d5857f8f304c52/Model_Card_Claude_3_Addendum.pdf) |
43-
| {% data variables.copilot.copilot_claude_sonnet_37 %} | Deep reasoning and debugging | Structured reasoning across large, complex codebases | Agent mode, vision | [{% data variables.copilot.copilot_claude_sonnet_37 %} model card](https://assets.anthropic.com/m/785e231869ea8b3b/original/claude-3-7-sonnet-system-card.pdf) |
4440
| {% data variables.copilot.copilot_claude_sonnet_40 %} | Deep reasoning and debugging | Performance and practicality, perfectly balanced for coding workflows | Agent mode, vision | [{% data variables.copilot.copilot_claude_sonnet_40 %} model card](https://www-cdn.anthropic.com/6be99a52cb68eb70eb9572b4cafad13df32ed995.pdf) |
4541
| {% data variables.copilot.copilot_gemini_25_pro %} | Deep reasoning and debugging | Complex code generation, debugging, and research workflows | Reasoning, vision | [{% data variables.copilot.copilot_gemini_25_pro %} model card](https://storage.googleapis.com/model-cards/documents/gemini-2.5-pro.pdf) |
46-
| {% data variables.copilot.copilot_gemini_flash %} | Working with visuals (diagrams, screenshots) | Real-time responses and visual reasoning for UI and diagram-based tasks | Vision | [{% data variables.copilot.copilot_gemini_flash %} model card](https://storage.googleapis.com/model-cards/documents/gemini-2-flash.pdf) |
4742
| {% data variables.copilot.copilot_grok_code %} | General-purpose coding and writing | Fast, accurate code completions and explanations | Agent mode | [{% data variables.copilot.copilot_grok_code %} model card](https://data.x.ai/2025-08-20-grok-4-model-card.pdf) |
4843
| {% data variables.copilot.copilot_qwen_25 %} | General-purpose coding and writing | Code generation, reasoning, and code repair / debugging | Reasoning | [{% data variables.copilot.copilot_qwen_25 %} model card](https://arxiv.org/pdf/2409.12186) |
4944

@@ -55,9 +50,6 @@ Use these models for common development tasks that require a balance of quality,
5550
|-------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------|
5651
| {% data variables.copilot.copilot_gpt_5_codex %} | Delivers higher-quality code on complex engineering tasks like features, tests, debugging, refactors, and reviews without lengthy instructions. |
5752
| {% data variables.copilot.copilot_gpt_5_mini %} | Reliable default for most coding and writing tasks. Fast, accurate, and works well across languages and frameworks. |
58-
| {% data variables.copilot.copilot_claude_sonnet_37 %} | Produces clear, structured output. Follows formatting instructions and maintains consistent style. |
59-
| {% data variables.copilot.copilot_gemini_flash %} | Fast and cost-effective. Well suited for quick questions, short code snippets, and lightweight writing tasks. |
60-
| {% data variables.copilot.copilot_o4_mini %} | Optimized for speed and cost efficiency. Ideal for real-time suggestions with low usage overhead. |
6153
| {% data variables.copilot.copilot_grok_code %} | Specialized for coding tasks. Performs well on code generation, and debugging across multiple languages. |
6254

6355
### When to use these models
@@ -81,10 +73,8 @@ These models are optimized for speed and responsiveness. They’re ideal for qui
8173

8274
| Model | Why it's a good fit |
8375
|-------------------------------------------------------|------------------------------------------------------------------------------------------------------------|
84-
| {% data variables.copilot.copilot_o4_mini %} | A quick and cost-effective model for repetitive or simple coding tasks. Offers clear, concise suggestions. |
8576
| {% data variables.copilot.copilot_claude_haiku_45 %} | Balances fast responses with quality output. Ideal for small tasks and lightweight code explanations. |
8677
| {% data variables.copilot.copilot_claude_sonnet_35 %} | Balances fast responses with quality output. Ideal for small tasks and lightweight code explanations. |
87-
| {% data variables.copilot.copilot_gemini_flash %} | Extremely low latency and multimodal support (where available). Great for fast, interactive feedback. |
8878

8979
### When to use these models
9080

@@ -110,11 +100,8 @@ These models are designed for tasks that require step-by-step reasoning, complex
110100
|-------------------------------------------------------|---------------------------------------------------------------------------------------------------------------|
111101
| {% 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. |
112102
| {% data variables.copilot.copilot_gpt_5 %} | Great at complex reasoning, code analysis, and technical decision-making. |
113-
| {% data variables.copilot.copilot_o3 %} | Strong at algorithm design, system debugging, and architecture decisions. Balances performance and reasoning. |
114-
| {% data variables.copilot.copilot_claude_sonnet_37 %} | Provides hybrid reasoning that adapts to both fast tasks and deeper thinking. |
115103
| {% data variables.copilot.copilot_claude_sonnet_40 %} | Improves on 3.7 with more reliable completions and smarter reasoning under pressure. |
116104
| {% data variables.copilot.copilot_claude_opus_41 %} | Anthropic’s most powerful model. Improves on {% data variables.copilot.copilot_claude_opus %}. |
117-
| {% data variables.copilot.copilot_claude_opus %} | Strong at strategy, debugging, and multi-layered logic. |
118105
| {% data variables.copilot.copilot_gemini_25_pro %} | Advanced reasoning across long contexts and scientific or technical analysis. |
119106

120107
### When to use these models
@@ -139,9 +126,7 @@ Use these models when you want to ask questions about screenshots, diagrams, UI
139126
| Model | Why it's a good fit |
140127
|-------|---------------------|
141128
| {% 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. |
142-
| {% data variables.copilot.copilot_claude_opus %} | Anthropic’s most powerful model. Strong at strategy, debugging, and multi-layered logic. |
143129
| {% data variables.copilot.copilot_claude_sonnet_40 %} | Improves on 3.7 with more reliable completions and smarter reasoning under pressure. |
144-
| {% data variables.copilot.copilot_gemini_flash %} | Fast, multimodal model optimized for real-time interaction. Useful for feedback on diagrams, visual prototypes, and UI layouts. |
145130
| {% data variables.copilot.copilot_gemini_25_pro %} | Deep reasoning and debugging, ideal for complex code generation, debugging, and research workflows. |
146131

147132
### When to use these models

0 commit comments

Comments
 (0)