docs/content/copilot/reference/ai-models/model-hosting.md

title, shortTitle, allowTitleToDifferFromFilename, intro, versions, topics, category, redirect_from, contentType

title	shortTitle	allowTitleToDifferFromFilename	intro	versions	topics	category	redirect_from	contentType
Hosting of models for GitHub Copilot Chat	Model hosting	true	Learn how different AI models are hosted for {% data variables.copilot.copilot_chat_short %}.	feature copilot	Copilot	Learn about Copilot	/copilot/reference/ai-models/how-copilot-serves-ai-models	reference

{% data variables.product.prodname_copilot %} can use a variety of AI models. This article explains how these models are hosted and served.

OpenAI models

Used for:

• {% data variables.copilot.copilot_gpt_41 %}
• {% data variables.copilot.copilot_gpt_5_codex %} (supported in {% data variables.product.prodname_vscode %} v1.104.1 or higher)
• {% data variables.copilot.copilot_gpt_5_mini %}
• {% data variables.copilot.copilot_gpt_5 %}

{% data variables.copilot.copilot_gpt_41 %} is hosted by {% data variables.product.github %}'s Azure tenant when used in {% data variables.product.prodname_copilot %}.

{% data variables.copilot.copilot_gpt_5_codex %}, {% data variables.copilot.copilot_gpt_5 %}, and {% data variables.copilot.copilot_gpt_5_mini %} models are hosted by OpenAI and {% data variables.product.github %}'s Azure tenant. OpenAI makes the following data commitment: We [OpenAI] do not train our models on your business data by default. {% data variables.product.github %} maintains a zero data retention agreement with OpenAI.

When using OpenAI's models, input requests and output responses continue to run through {% data variables.product.prodname_copilot %}'s content filters for public code matching, when applied, along with those for harmful or offensive content.

OpenAI models fine-tuned by Microsoft

Used for:

• {% data variables.copilot.copilot_raptor_mini %}

{% data variables.copilot.copilot_raptor_mini %} is deployed on {% data variables.product.github %} managed Azure OpenAI tenant.

Anthropic models

Used for:

• {% data variables.copilot.copilot_claude_haiku_45 %}
• {% data variables.copilot.copilot_claude_sonnet_45 %}
• {% data variables.copilot.copilot_claude_opus_41 %}
• {% data variables.copilot.copilot_claude_sonnet_40 %}

{% data variables.copilot.copilot_claude_haiku_45 %} and {% data variables.copilot.copilot_claude_opus_41 %} are hosted by Anthropic PBC. {% data variables.copilot.copilot_claude_sonnet_40 %} is hosted by Anthropic PBC and Google Cloud Platform. {% data variables.copilot.copilot_claude_sonnet_45 %} is hosted by Amazon Web Services, Anthropic PBC, and Google Cloud Platform. {% data variables.product.github %} has provider agreements in place to ensure data is not used for training. Additional details for each provider are included below:

• Amazon Bedrock: Amazon makes the following data commitments: Amazon Bedrock doesn't store or log your prompts and completions. Amazon Bedrock doesn't use your prompts and completions to train any AWS models and doesn't distribute them to third parties.
• Anthropic PBC: {% data variables.product.github %} maintains a zero data retention agreement with Anthropic.
• Google Cloud: Google commits to not training on {% data variables.product.github %} data as part of their service terms. {% data variables.product.github %} is additionally not subject to prompt logging for abuse monitoring.

To provide better service quality and reduce latency, {% data variables.product.github %} uses prompt caching. You can read more about prompt caching on Anthropic PBC, Amazon Bedrock, and Google Cloud.

When using {% data variables.copilot.copilot_claude %}, input prompts and output completions continue to run through {% data variables.product.prodname_copilot %}'s content filters for public code matching, when applied, along with those for harmful or offensive content.

Google models

Used for:

• {% data variables.copilot.copilot_gemini_25_pro %}

{% data variables.product.prodname_copilot %} uses {% data variables.copilot.copilot_gemini_25_pro %} hosted on Google Cloud Platform (GCP). When using {% data variables.copilot.copilot_gemini %} models, prompts and metadata are sent to GCP, which makes the following data commitment: {% data variables.copilot.copilot_gemini %} doesn't use your prompts, or its responses, as data to train its models.

To provide better service quality and reduce latency, {% data variables.product.github %} uses prompt caching.

When using {% data variables.copilot.copilot_gemini %} models, input prompts and output completions continue to run through {% data variables.product.prodname_copilot %}'s content filters for public code matching, when applied, along with those for harmful or offensive content.

xAI models

{% data reusables.copilot.grok-promo-period %}

{% data variables.copilot.copilot_grok_code %} is hosted by xAI when used in {% data variables.product.prodname_copilot %}.

xAI operates {% data variables.copilot.copilot_grok_code %} in {% data variables.product.prodname_copilot %} under a zero data retention API policy. This means xAI commits that user content (both inputs sent to the model and outputs generated by the model):

Will not be:

• Logged for any purpose, including human review
• Saved to disk or retained in any form, including as metadata
• Accessible by xAI personnel
• Used for model training

Will only:

• Exist temporarily in RAM for the minimum time required to process and respond to each request
• Be immediately deleted from memory once the response is delivered

When using xAI, input prompts and output completions continue to run through {% data variables.product.prodname_copilot %}'s content filters for public code matching, when applied, along with those for harmful or offensive content.

For more information, see xAI's enterprise terms of service on the xAI website.