| title | Supported AI models in GitHub Copilot | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| shortTitle | Supported models | ||||||||||
| allowTitleToDifferFromFilename | true | ||||||||||
| intro | Learn about the supported AI models in {% data variables.product.prodname_copilot %}. | ||||||||||
| versions |
|
||||||||||
| category |
|
||||||||||
| redirect_from |
|
||||||||||
| contentType | reference |
{% data variables.product.prodname_copilot %} supports multiple AI models, each with different strengths. Some prioritize speed and cost-efficiency, while others are optimized for accuracy, reasoning, or multimodal inputs. The right model depends on your task. For a side-by-side comparison to help you choose, see AUTOTITLE.
The models available to you depend on your {% data variables.product.prodname_copilot_short %} plan and where you're using {% data variables.product.prodname_copilot_short %}, such as {% data variables.product.prodname_dotcom_the_website %} or an IDE.
Note
Model availability is subject to change. Some models may be replaced or updated over time.
For all of the default AI models, input prompts and output completions run through {% data variables.product.prodname_copilot %}'s content filters for harmful, offensive, or off-topic content, and for public code matching when enabled.
This table lists the AI models available in {% data variables.product.prodname_copilot_short %}, along with their release status.
{% rowheaders %}
| Model name | Provider | Release status |
|---|---|---|
| {% for model in tables.copilot.model-release-status %} | ||
| {{ model.name }}{% if model.name == 'GPT-5.4 nano' %}[^gpt54nano]{% endif %}{% if model.name == 'MAI-Code-1-Flash' or model.name == 'MAI-Code-1.1-Flash' %}1{% endif %}{% if model.name == 'Claude Fable 5' or model.name == 'Claude Fable 5.1' %}2{% endif %} | {{ model.provider }} | {{ model.release_status }} |
| {% endfor %} |
{% endrowheaders %}
This table lists the supported AI models for {% data variables.copilot.copilot_auto_model_selection_short_cap_a %}. Available models may be limited by model policies. For example, as the long term support model, GPT-5.3-Codex will be used in the event no other models are available. SeeAUTOTITLE and AUTOTITLE.
{% rowheaders %}
| Model | {% data variables.copilot.copilot_cloud_agent %} | {% data variables.copilot.copilot_chat_short %} | {% data variables.copilot.copilot_cli_short %} | {% data variables.copilot.github_copilot_app %} |
|---|---|---|---|---|
| {% for model in tables.copilot.auto-model-selection %} | ||||
| {{ model.name }} | {% if model.cloud_agent == true %}{% octicon "check" aria-label="Included" %}{% else %}{% octicon "x" aria-label="Not included" %}{% endif %} | {% if model.chat == true %}{% octicon "check" aria-label="Included" %}{% else %}{% octicon "x" aria-label="Not included" %}{% endif %} | {% if model.cli == true %}{% octicon "check" aria-label="Included" %}{% else %}{% octicon "x" aria-label="Not included" %}{% endif %} | {% if model.app == true %}{% octicon "check" aria-label="Included" %}{% else %}{% octicon "x" aria-label="Not included" %}{% endif %} |
| {% endfor %} |
{% endrowheaders %}
The latest {% data variables.product.prodname_copilot_short %} models support the following extended capabilities.
- 1 million token context window: Allows the model to process significantly more content in a single session. This is useful when working across large codebases, long documents, or complex multi-file projects. When you select a supported model, you can choose between the default context size or the extended (1 million token) context.
- Configurable reasoning levels: Controls the depth of the model's reasoning process before it generates a response. When you select a supported model, you can choose which reasoning level you want to use. Higher reasoning levels can improve the quality of responses to complex problems.
Choosing a larger context window or higher reasoning will impact {% data variables.product.prodname_ai_credits_short %} consumption; more tokens will be consumed, so more credits will be used. For this reason, we recommend that you use the regular context window and regular reasoning by default, selecting the larger context window and higher reasoning for more complex tasks only.
Note
- The 1 million token context window is available in {% data variables.product.prodname_vscode %} and {% data variables.copilot.copilot_cli_short %} only.
- Configurable reasoning levels are available in {% data variables.product.prodname_vscode %}, {% data variables.copilot.copilot_cli_short %}, and {% data variables.copilot.copilot_cloud_agent %}.
- Some models have extended capability pricing see AUTOTITLE
{% rowheaders %}
| Model | 1 million token context window | Configurable reasoning |
|---|---|---|
| {% data variables.copilot.copilot_claude_sonnet_46 %} | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
| {% data variables.copilot.copilot_claude_opus_47 %} | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
| {% data variables.copilot.copilot_claude_opus_48 %} | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
| {% data variables.copilot.copilot_claude_opus_5 %} | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
| {% data variables.copilot.copilot_claude_sonnet_5 %} | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
| {% data variables.copilot.copilot_claude_opus_48_fast %} | {% octicon "x" aria-label="Not supported" %} | {% octicon "check" aria-label="Supported" %} |
| {% data variables.copilot.copilot_claude_fable_5 %} | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
| {% data variables.copilot.copilot_claude_fable_51 %} | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
| {% data variables.copilot.copilot_gpt_53_codex %} | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
| {% data variables.copilot.copilot_gpt_54 %} | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
| {% data variables.copilot.copilot_gpt_55 %} | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
| {% data variables.copilot.copilot_gpt_56_luna %} | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
| {% data variables.copilot.copilot_gpt_56_sol %} | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
| {% data variables.copilot.copilot_gpt_56_terra %} | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
| {% data variables.copilot.copilot_gpt_6_astra %} | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
| {% data variables.copilot.copilot_kimi_k3 %} | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
{% endrowheaders %}
The following table shows which models are available in each client.
{% rowheaders %}
| Model | {% data variables.product.prodname_dotcom_the_website %} | {% data variables.copilot.copilot_cli_short %} | {% data variables.product.prodname_vscode %} | {% data variables.product.prodname_vs %} | Eclipse | Xcode | JetBrains IDEs |
|---|---|---|---|---|---|---|---|
| {% for model in tables.copilot.model-supported-clients %} | |||||||
| {{ model.name }}{% if model.name == 'GPT-5.4 nano' %}[^gpt54nano]{% endif %} | {% if model.dotcom == true %}{% octicon "check" aria-label="Included" %}{% else %}{% octicon "x" aria-label="Not included" %}{% endif %} | {% if model.cli == true %}{% octicon "check" aria-label="Included" %}{% else %}{% octicon "x" aria-label="Not included" %}{% endif %} | {% if model.vscode == true %}{% octicon "check" aria-label="Included" %}{% else %}{% octicon "x" aria-label="Not included" %}{% endif %} | {% if model.vs == true %}{% octicon "check" aria-label="Included" %}{% else %}{% octicon "x" aria-label="Not included" %}{% endif %} | {% if model.eclipse == true %}{% octicon "check" aria-label="Included" %}{% else %}{% octicon "x" aria-label="Not included" %}{% endif %} | {% if model.xcode == true %}{% octicon "check" aria-label="Included" %}{% else %}{% octicon "x" aria-label="Not included" %}{% endif %} | {% if model.jetbrains == true %}{% octicon "check" aria-label="Included" %}{% else %}{% octicon "x" aria-label="Not included" %}{% endif %} |
| {% endfor %} |
{% endrowheaders %}
Note
In {% data variables.product.prodname_vscode %} you can add more models than those that are available by default with your {% data variables.product.prodname_copilot_short %} subscription. See AUTOTITLE.
Some {% data variables.product.prodname_copilot_short %} models require minimum versions of supported IDEs or {% data variables.product.prodname_copilot_short %} extensions or plugins. The table below lists the minimum versions known from changelog entries or provided release guidance. This information is tentative and subject to change as model support rolls out. For best results, keep your IDE and {% data variables.product.prodname_copilot_short %} extension or plugin updated to the latest available version.
{% rowheaders %}
| Model | {% data variables.product.prodname_vscode %} | {% data variables.product.prodname_vs %} | JetBrains IDEs | Xcode | Eclipse |
|---|---|---|---|---|---|
| {% data variables.copilot.copilot_gemini_35_flash %} | v1.115.0 |
17.14.22 or 18.1.0 |
1.5.62 |
0.46.0 |
0.14.0 |
| {% data variables.copilot.copilot_gemini_36_flash %} | v1.128.0 |
17.14.22 or 18.1.0 |
TBD | TBD | TBD |
| {% data variables.copilot.copilot_gemini_37_flash %} | v1.128.0 |
17.14.22 or 18.1.0 |
TBD | TBD | TBD |
| {% data variables.copilot.copilot_gemini_38_flash %} | TBD | 17.14.22 or 18.1.0 |
TBD | TBD | TBD |
| {% data variables.copilot.copilot_gpt_52_codex %} | No minimum listed | 17.14.19 or 18.0.0 |
1.5.61 |
0.45.0 |
0.13.0 |
| {% data variables.copilot.copilot_gpt_53_codex %} | v1.104.1 |
17.14.19 |
1.5.61 |
0.45.0 |
0.13.0 |
| {% data variables.copilot.copilot_gpt_54 %} | v1.104.1 |
17.14.19 |
1.5.66 |
0.47.0 |
0.15.0 |
| {% data variables.copilot.copilot_gpt_54_mini %} | v1.104.1 |
17.14.19 |
1.5.66 |
0.47.0 |
0.15.0 |
| {% data variables.copilot.copilot_gpt_55 %} | v1.117 |
17.14.19 |
1.5.66 |
0.47.0 |
0.15.0 |
| {% data variables.copilot.copilot_gpt_56_luna %} | 1.128.0 |
TBD | TBD | TBD | TBD |
| {% data variables.copilot.copilot_gpt_56_sol %} | 1.128.0 |
TBD | TBD | TBD | TBD |
| {% data variables.copilot.copilot_gpt_56_terra %} | 1.128.0 |
TBD | TBD | TBD | TBD |
| {% data variables.copilot.copilot_gpt_6_astra %} | 1.136.1 |
17.14.19 |
TBD | TBD | TBD |
| {% data variables.copilot.copilot_claude_opus_48 %} | v1.118 |
17.14.6 |
TBD | TBD | TBD |
| {% data variables.copilot.copilot_claude_opus_5 %} | v1.128.0 |
17.14.22 |
TBD | TBD | TBD |
| {% data variables.copilot.copilot_claude_sonnet_5 %} | v1.124 |
17.14.6 |
TBD | TBD | TBD |
| {% data variables.copilot.copilot_claude_fable_5 %} | v1.124 |
17.14.6 |
TBD | TBD | TBD |
| {% data variables.copilot.copilot_claude_fable_51 %} | TBD | TBD | TBD | TBD | TBD |
| {% data variables.copilot.copilot_kimi_k27_code %} | v1.127 |
17.14.6 |
1.9.1-251 |
TBD | TBD |
| {% data variables.copilot.copilot_kimi_k3 %} | v1.131 |
TBD | TBD | TBD | TBD |
| {% data variables.copilot.copilot_mai_code_1_flash %} | v1.121 |
TBD | TBD | TBD | TBD |
| {% data variables.copilot.copilot_mai_code_1_1_flash %} | v1.121 |
TBD | TBD | TBD | TBD |
| {% data variables.copilot.copilot_grok_45 %} | TBD | 17.14.19 |
TBD | TBD | TBD |
| {% data variables.copilot.copilot_grok_46 %} | TBD | TBD | TBD | TBD | TBD |
{% endrowheaders %}
Note
- For {% data variables.copilot.copilot_gpt_53_codex %} in {% data variables.product.prodname_vscode %},
v1.108and later provide improved prompting and response quality. - "No minimum listed" means the reviewed changelog or release guidance did not specify a minimum version, not that all older versions are supported.
- Even when a model appears in the model picker on older supported versions, prompting and model behavior may work best with the latest IDE and {% data variables.product.prodname_copilot_short %} extension or plugin versions.
The following table shows which AI models are available in each {% data variables.product.prodname_copilot_short %} plan. For more information about the plans, see AUTOTITLE.
{% data reusables.copilot.available-models-per-plan %}
Note
- If you're an organization or enterprise owner, you can enable or restrict access to specific models for your members. See AUTOTITLE.
For more information about fallback and LTS models, see AUTOTITLE.
{% data variables.product.prodname_copilot %} offers access to evaluation models.
Important
- Testing revealed evaluation models may perform worse than other models on security-related, or other categories of prompts.
- Users should always carefully review and validate code, including code security, using a range of models and with a thorough human review before incorporating suggestions into production.
Evaluation models may appear in the product with codenames rather than official model or provider names. These models come from or are fine-tuned by one or more of the following providers: Microsoft, OpenAI, Anthropic, and Google. Data handling for each provider is limited to {% data variables.product.github %}'s existing agreement with that provider, and evaluation models undergo {% data variables.product.github %} and Microsoft testing and verification before release.
Evaluation models may be added, updated, or removed without notice. Availability and rate limits may differ from generally available models.
Access to evaluation models in {% data variables.copilot.copilot_auto_model_selection_short %} for users {% data variables.product.prodname_copilot_short %} plans for individuals is governed by a policy. To disable evaluation models:
{% data reusables.user-settings.access_settings %} {% data reusables.enterprise-accounts.ai-controls-tab %}
- For the Evaluation models in {% data variables.product.prodname_copilot_short %} {% data variables.copilot.copilot_auto_model_selection_short %} setting, select Disabled from the dropdown.
Utility models power background features across surfaces, and cannot be disabled or selected in the model picker. See AUTOTITLE.
{% data reusables.copilot.utility-models %}
{% data reusables.copilot.model-autoenablement %}
{% data reusables.copilot.model-autoenablement-excluded-models %}
If a particular model seems unavailable, refer to the model vendor's support page for the latest information about its availability. If more than one model from different vendors is unavailable, contact {% data variables.contact.contact_support_page %} or refer to the GitHub status page for additional information.
The following table lists AI models that are retired or scheduled for retirement from {% data variables.product.prodname_copilot_short %}, along with their retirement dates and suggested alternatives.
{% rowheaders %}
| Model name | Retirement date | Suggested alternative |
|---|---|---|
| {% for model in tables.copilot.model-deprecation-history %} | ||
| {{ model.name }}{% if model.name == 'Claude Sonnet 4.6' %}3{% endif %} | {{ model.retirement_date }} | {{ model.suggested_alternative }} |
| {% endfor %} |
{% endrowheaders %}
- To get up and running with {% data variables.product.prodname_copilot_short %}, see AUTOTITLE.
- To configure which models are available to you, see AUTOTITLE.
- To learn more about Responsible Use and Responsible AI, see {% data variables.product.prodname_copilot_short %} Trust Center and AUTOTITLE.
Footnotes
-
MAI models are continuously improving models. Performance and behavior may evolve over time as new checkpoints are released. ↩
-
When {% data variables.copilot.copilot_claude_fable_5 %} or {% data variables.copilot.copilot_claude_fable_51 %} is used, Anthropic retains data, including prompts and outputs, by default to operate safety classifiers that detect harmful use. Customers can request to use {% data variables.copilot.copilot_claude_fable_5 %} or {% data variables.copilot.copilot_claude_fable_51 %} with zero data retention (ZDR) through the end of 2026 under a time-bound exemption while Anthropic rolls out Enterprise Frontier Safeguards (EFS). After that point, continued use of these models would require EFS, which will enable eligible customers to keep their data under their own control while also enabling automated safety monitoring. For an enterprise that has been approved and configured for this type of access, {% data variables.copilot.copilot_claude_fable_5 %} and {% data variables.copilot.copilot_claude_fable_51 %} requests will use the ZDR endpoint through the end of 2026 when the models are enabled. To learn whether your enterprise is eligible and request access, contact your {% data variables.product.github %} account team. Approval for access does not automatically enable {% data variables.copilot.copilot_claude_fable_5 %} or {% data variables.copilot.copilot_claude_fable_51 %}. An enterprise or organization administrator must still enable each model before users can access it. Other Claude models, except for {% data variables.copilot.copilot_claude_fable_5 %} and {% data variables.copilot.copilot_claude_fable_51 %}, continue to operate under ZDR. Customers who enable a Fable model with ZDR agree to use this model only for internal operations, including to develop and evaluate products for their own customers. They may not make the model endpoints or outputs available externally. To enable these models, see AUTOTITLE. ↩
-
{% data variables.copilot.copilot_claude_sonnet_46 %} remains available to individual {% data variables.product.prodname_copilot_short %} subscribers on annual plans. The retirement of {% data variables.copilot.copilot_claude_sonnet_46 %} does not apply to these subscribers. ↩