From 84fd87cd029e3fe84d63c5d017bc8d99c323db26 Mon Sep 17 00:00:00 2001 From: hongyi-chen Date: Tue, 9 Jun 2026 18:11:26 +0000 Subject: [PATCH 1/3] docs: add Claude Fable 5 and its data retention requirement Document Claude Fable 5 in the model choice docs, including that Anthropic requires limited data retention for this model, so it is not available under Zero Data Retention (ZDR). - model-choice: add Claude Fable 5 to the Anthropic table, a caution callout, and a ZDR carveout sentence - security-overview: note model-specific retention requirements and the Enterprise off-by-default behavior - admin-panel: add a Models section covering availability control and retention-required models (off by default, admin-enabled) - pricing-faqs: add the ZDR carveout to the provider-ZDR Q&As Co-Authored-By: Oz --- .../agent-platform/inference/model-choice.mdx | 11 +++++++++++ .../security-overview.mdx | 2 ++ .../enterprise/team-management/admin-panel.mdx | 16 +++++++++++++++- .../plans-and-billing/pricing-faqs.mdx | 4 +++- 4 files changed, 31 insertions(+), 2 deletions(-) diff --git a/src/content/docs/agent-platform/inference/model-choice.mdx b/src/content/docs/agent-platform/inference/model-choice.mdx index a44f2f33..b1ceb764 100644 --- a/src/content/docs/agent-platform/inference/model-choice.mdx +++ b/src/content/docs/agent-platform/inference/model-choice.mdx @@ -55,8 +55,13 @@ All Auto models perform well across all agent workflows and are ideal if you pre #### Anthropic +Claude Fable 5 is Anthropic's newest generally available model for autonomous, long-running coding and knowledge work. + | Model | `model_id` | Variant | | --- | --- | --- | +| Claude Fable 5 | `claude-5-fable-xhigh` | Default effort | +| Claude Fable 5 | `claude-5-fable-high` | High effort | +| Claude Fable 5 | `claude-5-fable-max` | Max effort | | Claude Opus 4.7 | `claude-4-7-opus-xhigh` | Default effort | | Claude Opus 4.7 | `claude-4-7-opus-high` | High effort | | Claude Opus 4.7 | `claude-4-7-opus-max` | Max effort | @@ -70,6 +75,10 @@ All Auto models perform well across all agent workflows and are ideal if you pre | Claude Sonnet 4.5 | `claude-4-5-sonnet-thinking` | Thinking on | | Claude Haiku 4.5 | `claude-4-5-haiku` | — | +:::caution +Anthropic requires limited data retention for Claude Fable 5 for safety, abuse monitoring, and compliance reasons. As a result, Claude Fable 5 is **not available under Zero Data Retention (ZDR)**. This requirement is specific to Claude Fable 5 and does not change the ZDR behavior of any other supported model. For Enterprise teams, Claude Fable 5 is off by default and a workspace admin must enable it — see [Admin Panel](/enterprise/team-management/admin-panel/#models) and the [Security overview](/enterprise/security-and-compliance/security-overview/#zero-data-retention-zdr). +::: + #### Google | Model | `model_id` | @@ -133,3 +142,5 @@ Warp has executed **Zero Data Retention (ZDR)** agreements with these providers. * LLM providers commit to delete inputs and outputs after generating the relevant output, within a fixed time period. Warp enforces these commitments through both technical measures and contractual safeguards with the LLM providers. + +Zero data retention is available for supported models. Model availability may vary where providers require limited data retention for safety, abuse monitoring, or compliance reasons. For example, Anthropic requires limited data retention for [Claude Fable 5](#anthropic), so it is not available under ZDR; this applies only to that model and does not change the ZDR behavior of other supported models. diff --git a/src/content/docs/enterprise/security-and-compliance/security-overview.mdx b/src/content/docs/enterprise/security-and-compliance/security-overview.mdx index 2c8ba553..67167aed 100644 --- a/src/content/docs/enterprise/security-and-compliance/security-overview.mdx +++ b/src/content/docs/enterprise/security-and-compliance/security-overview.mdx @@ -34,6 +34,8 @@ How data collection works by plan: Some product features — including cloud conversations and Oz runs — require storing conversation data to function. This data is stored to power the product experience and is separate from analytics or telemetry data collection. ::: +Some models carry provider-specific data retention requirements and are therefore not covered by ZDR. For example, Anthropic requires limited data retention for [Claude Fable 5](/agent-platform/inference/model-choice/#anthropic) for safety, abuse monitoring, and compliance reasons. For Enterprise teams, these models are **off by default**; a workspace admin must explicitly enable them in the [Admin Panel](/enterprise/team-management/admin-panel/#models). This applies only to the affected model and does not change the ZDR behavior of other supported models. + Enterprise subscriptions also include: * **Team-level enforcement** - Admins configure data collection and telemetry policies for the entire organization through the Admin Panel diff --git a/src/content/docs/enterprise/team-management/admin-panel.mdx b/src/content/docs/enterprise/team-management/admin-panel.mdx index 6131200f..489e9513 100644 --- a/src/content/docs/enterprise/team-management/admin-panel.mdx +++ b/src/content/docs/enterprise/team-management/admin-panel.mdx @@ -110,7 +110,7 @@ For complete plan details, see [Warp pricing](https://www.warp.dev/pricing) or [ ## Admin Panel sections -The Admin Panel is organized into six main areas: +The Admin Panel is organized into seven main areas: ### AI settings @@ -211,6 +211,20 @@ When enabled, agents understand your code patterns, architecture, and convention * Up to 200,000 files per repository * Team-wide indexing with centralized configuration +### Models + +Control which LLM models are available to your team and how inference is routed. From the **Models** page, admins can enable or disable individual models and configure [Bring Your Own LLM (BYOLLM)](/enterprise/enterprise-features/bring-your-own-llm/) routing through AWS Bedrock. + +**Models with provider-specific data retention requirements** + +Some models require limited data retention from the model provider and are therefore not available under [Zero Data Retention (ZDR)](/enterprise/security-and-compliance/security-overview/#zero-data-retention-zdr). For Enterprise teams, these models are **disabled by default**. A workspace admin must explicitly enable them before team members can use them. + +For example, [Claude Fable 5](/agent-platform/inference/model-choice/#anthropic) requires data retention. When you enable it, Warp surfaces a helper note: + +> Anthropic requires data retention for this model for a limited time for safety, abuse monitoring, and compliance reasons. + +Leave these models disabled if your organization has strict ZDR requirements. Enabling a model applies only to that model and does not change the ZDR behavior of other supported models. + ### Billing settings Configure billing preferences and spending controls to manage costs at scale. diff --git a/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx b/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx index 6b2a8f5f..c37b8430 100644 --- a/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx +++ b/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx @@ -242,6 +242,8 @@ Warp integrates with multiple LLM providers — including Anthropic, OpenAI, Goo Warp enforces these commitments through both technical measures and contractual safeguards with the LLM providers. +Zero data retention is available for supported models. Model availability may vary where providers require limited data retention for safety, abuse monitoring, or compliance reasons. For example, Anthropic requires limited data retention for [Claude Fable 5](/agent-platform/inference/model-choice/#anthropic), so it isn't available under ZDR. This applies only to that model and doesn't change the ZDR behavior of other supported models. + ### How can I enable Zero Data Retention in Warp? Zero Data Retention (ZDR) can be enabled in two ways: @@ -251,7 +253,7 @@ Zero Data Retention (ZDR) can be enabled in two ways: To discuss organization-wide ZDR for your team, [contact our sales team](https://www.warp.dev/contact-sales). -Regardless of plan, Warp never allows OpenAI, Anthropic, Google, or other model providers to store, retain, or train their models on your data — see [Does Warp have Zero Data Retention policies with LLM providers?](#does-warp-have-zero-data-retention-policies-with-llm-providers) for details. +Regardless of plan, Warp never allows OpenAI, Anthropic, Google, or other model providers to store, retain, or train their models on your data — see [Does Warp have Zero Data Retention policies with LLM providers?](#does-warp-have-zero-data-retention-policies-with-llm-providers) for details. A small number of models are an exception where the provider requires limited data retention for safety, abuse monitoring, or compliance reasons (for example, [Claude Fable 5](/agent-platform/inference/model-choice/#anthropic)); these are clearly identified and, for Enterprise teams, off by default. ### Can I bring my own API key? From 66a0cd4e9c13e9e9db88bef64f59cacbfb359ac4 Mon Sep 17 00:00:00 2001 From: hongyi-chen Date: Tue, 9 Jun 2026 18:15:56 +0000 Subject: [PATCH 2/3] docs: trim Fable 5 retention copy and drop "limited" Address review feedback: - Remove the Claude Fable 5 model description line in model-choice - Drop the redundant Fable 5 example/helper-note block in admin-panel - Drop the redundant Fable 5 example sentence from the model-choice and pricing-faqs ZDR sections - Use "data retention" instead of "limited data retention" throughout Co-Authored-By: Oz --- .../docs/agent-platform/inference/model-choice.mdx | 6 ++---- .../security-and-compliance/security-overview.mdx | 2 +- .../docs/enterprise/team-management/admin-panel.mdx | 8 +------- .../plans-and-billing/pricing-faqs.mdx | 4 ++-- 4 files changed, 6 insertions(+), 14 deletions(-) diff --git a/src/content/docs/agent-platform/inference/model-choice.mdx b/src/content/docs/agent-platform/inference/model-choice.mdx index b1ceb764..f61d4684 100644 --- a/src/content/docs/agent-platform/inference/model-choice.mdx +++ b/src/content/docs/agent-platform/inference/model-choice.mdx @@ -55,8 +55,6 @@ All Auto models perform well across all agent workflows and are ideal if you pre #### Anthropic -Claude Fable 5 is Anthropic's newest generally available model for autonomous, long-running coding and knowledge work. - | Model | `model_id` | Variant | | --- | --- | --- | | Claude Fable 5 | `claude-5-fable-xhigh` | Default effort | @@ -76,7 +74,7 @@ Claude Fable 5 is Anthropic's newest generally available model for autonomous, l | Claude Haiku 4.5 | `claude-4-5-haiku` | — | :::caution -Anthropic requires limited data retention for Claude Fable 5 for safety, abuse monitoring, and compliance reasons. As a result, Claude Fable 5 is **not available under Zero Data Retention (ZDR)**. This requirement is specific to Claude Fable 5 and does not change the ZDR behavior of any other supported model. For Enterprise teams, Claude Fable 5 is off by default and a workspace admin must enable it — see [Admin Panel](/enterprise/team-management/admin-panel/#models) and the [Security overview](/enterprise/security-and-compliance/security-overview/#zero-data-retention-zdr). +Anthropic requires data retention for Claude Fable 5 for safety, abuse monitoring, and compliance reasons. As a result, Claude Fable 5 is **not available under Zero Data Retention (ZDR)**. This requirement is specific to Claude Fable 5 and does not change the ZDR behavior of any other supported model. For Enterprise teams, Claude Fable 5 is off by default and a workspace admin must enable it — see [Admin Panel](/enterprise/team-management/admin-panel/#models) and the [Security overview](/enterprise/security-and-compliance/security-overview/#zero-data-retention-zdr). ::: #### Google @@ -143,4 +141,4 @@ Warp has executed **Zero Data Retention (ZDR)** agreements with these providers. Warp enforces these commitments through both technical measures and contractual safeguards with the LLM providers. -Zero data retention is available for supported models. Model availability may vary where providers require limited data retention for safety, abuse monitoring, or compliance reasons. For example, Anthropic requires limited data retention for [Claude Fable 5](#anthropic), so it is not available under ZDR; this applies only to that model and does not change the ZDR behavior of other supported models. +Zero data retention is available for supported models. Model availability may vary where providers require data retention for safety, abuse monitoring, or compliance reasons. diff --git a/src/content/docs/enterprise/security-and-compliance/security-overview.mdx b/src/content/docs/enterprise/security-and-compliance/security-overview.mdx index 67167aed..e25561f9 100644 --- a/src/content/docs/enterprise/security-and-compliance/security-overview.mdx +++ b/src/content/docs/enterprise/security-and-compliance/security-overview.mdx @@ -34,7 +34,7 @@ How data collection works by plan: Some product features — including cloud conversations and Oz runs — require storing conversation data to function. This data is stored to power the product experience and is separate from analytics or telemetry data collection. ::: -Some models carry provider-specific data retention requirements and are therefore not covered by ZDR. For example, Anthropic requires limited data retention for [Claude Fable 5](/agent-platform/inference/model-choice/#anthropic) for safety, abuse monitoring, and compliance reasons. For Enterprise teams, these models are **off by default**; a workspace admin must explicitly enable them in the [Admin Panel](/enterprise/team-management/admin-panel/#models). This applies only to the affected model and does not change the ZDR behavior of other supported models. +Some models carry provider-specific data retention requirements and are therefore not covered by ZDR. For example, Anthropic requires data retention for [Claude Fable 5](/agent-platform/inference/model-choice/#anthropic). For Enterprise teams, these models are **off by default**; a workspace admin must explicitly enable them in the [Admin Panel](/enterprise/team-management/admin-panel/#models). Enterprise subscriptions also include: diff --git a/src/content/docs/enterprise/team-management/admin-panel.mdx b/src/content/docs/enterprise/team-management/admin-panel.mdx index 489e9513..b3c6d6f3 100644 --- a/src/content/docs/enterprise/team-management/admin-panel.mdx +++ b/src/content/docs/enterprise/team-management/admin-panel.mdx @@ -217,13 +217,7 @@ Control which LLM models are available to your team and how inference is routed. **Models with provider-specific data retention requirements** -Some models require limited data retention from the model provider and are therefore not available under [Zero Data Retention (ZDR)](/enterprise/security-and-compliance/security-overview/#zero-data-retention-zdr). For Enterprise teams, these models are **disabled by default**. A workspace admin must explicitly enable them before team members can use them. - -For example, [Claude Fable 5](/agent-platform/inference/model-choice/#anthropic) requires data retention. When you enable it, Warp surfaces a helper note: - -> Anthropic requires data retention for this model for a limited time for safety, abuse monitoring, and compliance reasons. - -Leave these models disabled if your organization has strict ZDR requirements. Enabling a model applies only to that model and does not change the ZDR behavior of other supported models. +Some models require data retention from the model provider and are therefore not available under [Zero Data Retention (ZDR)](/enterprise/security-and-compliance/security-overview/#zero-data-retention-zdr). For Enterprise teams, these models are **disabled by default**. A workspace admin must explicitly enable them before team members can use them. For example, [Claude Fable 5](/agent-platform/inference/model-choice/#anthropic) requires data retention. ### Billing settings diff --git a/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx b/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx index c37b8430..218c7aba 100644 --- a/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx +++ b/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx @@ -242,7 +242,7 @@ Warp integrates with multiple LLM providers — including Anthropic, OpenAI, Goo Warp enforces these commitments through both technical measures and contractual safeguards with the LLM providers. -Zero data retention is available for supported models. Model availability may vary where providers require limited data retention for safety, abuse monitoring, or compliance reasons. For example, Anthropic requires limited data retention for [Claude Fable 5](/agent-platform/inference/model-choice/#anthropic), so it isn't available under ZDR. This applies only to that model and doesn't change the ZDR behavior of other supported models. +Zero data retention is available for supported models. Model availability may vary where providers require data retention for safety, abuse monitoring, or compliance reasons. ### How can I enable Zero Data Retention in Warp? @@ -253,7 +253,7 @@ Zero Data Retention (ZDR) can be enabled in two ways: To discuss organization-wide ZDR for your team, [contact our sales team](https://www.warp.dev/contact-sales). -Regardless of plan, Warp never allows OpenAI, Anthropic, Google, or other model providers to store, retain, or train their models on your data — see [Does Warp have Zero Data Retention policies with LLM providers?](#does-warp-have-zero-data-retention-policies-with-llm-providers) for details. A small number of models are an exception where the provider requires limited data retention for safety, abuse monitoring, or compliance reasons (for example, [Claude Fable 5](/agent-platform/inference/model-choice/#anthropic)); these are clearly identified and, for Enterprise teams, off by default. +Regardless of plan, Warp never allows OpenAI, Anthropic, Google, or other model providers to store, retain, or train their models on your data — see [Does Warp have Zero Data Retention policies with LLM providers?](#does-warp-have-zero-data-retention-policies-with-llm-providers) for details. A small number of models are an exception where the provider requires data retention for safety, abuse monitoring, or compliance reasons (for example, [Claude Fable 5](/agent-platform/inference/model-choice/#anthropic)); these are clearly identified and, for Enterprise teams, off by default. ### Can I bring my own API key? From 40fad77c4a4c63a2b062f514ad5c6aacde0d10ca Mon Sep 17 00:00:00 2001 From: hongyi-chen Date: Tue, 9 Jun 2026 18:20:18 +0000 Subject: [PATCH 3/3] docs: drop remaining Fable 5 examples and polish - Remove the remaining Fable 5 example sentences from security-overview, admin-panel, and pricing-faqs (general carveout language is retained) - Polish: tighten the model-choice caution callout, rename the admin "Models" heading to "Models settings" for sibling consistency, and update cross-links to the #models-settings anchor Co-Authored-By: Oz --- src/content/docs/agent-platform/inference/model-choice.mdx | 2 +- .../enterprise/security-and-compliance/security-overview.mdx | 2 +- src/content/docs/enterprise/team-management/admin-panel.mdx | 4 ++-- .../support-and-community/plans-and-billing/pricing-faqs.mdx | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) diff --git a/src/content/docs/agent-platform/inference/model-choice.mdx b/src/content/docs/agent-platform/inference/model-choice.mdx index f61d4684..3c0651e9 100644 --- a/src/content/docs/agent-platform/inference/model-choice.mdx +++ b/src/content/docs/agent-platform/inference/model-choice.mdx @@ -74,7 +74,7 @@ All Auto models perform well across all agent workflows and are ideal if you pre | Claude Haiku 4.5 | `claude-4-5-haiku` | — | :::caution -Anthropic requires data retention for Claude Fable 5 for safety, abuse monitoring, and compliance reasons. As a result, Claude Fable 5 is **not available under Zero Data Retention (ZDR)**. This requirement is specific to Claude Fable 5 and does not change the ZDR behavior of any other supported model. For Enterprise teams, Claude Fable 5 is off by default and a workspace admin must enable it — see [Admin Panel](/enterprise/team-management/admin-panel/#models) and the [Security overview](/enterprise/security-and-compliance/security-overview/#zero-data-retention-zdr). +Anthropic requires data retention for Claude Fable 5 for safety, abuse monitoring, and compliance reasons, so it is **not available under Zero Data Retention (ZDR)**. This requirement is specific to Claude Fable 5 and doesn't change the ZDR behavior of any other supported model. For Enterprise teams, the model is off by default and a workspace admin must enable it — see the [Admin Panel](/enterprise/team-management/admin-panel/#models-settings) and the [Security overview](/enterprise/security-and-compliance/security-overview/#zero-data-retention-zdr). ::: #### Google diff --git a/src/content/docs/enterprise/security-and-compliance/security-overview.mdx b/src/content/docs/enterprise/security-and-compliance/security-overview.mdx index e25561f9..6eaf2652 100644 --- a/src/content/docs/enterprise/security-and-compliance/security-overview.mdx +++ b/src/content/docs/enterprise/security-and-compliance/security-overview.mdx @@ -34,7 +34,7 @@ How data collection works by plan: Some product features — including cloud conversations and Oz runs — require storing conversation data to function. This data is stored to power the product experience and is separate from analytics or telemetry data collection. ::: -Some models carry provider-specific data retention requirements and are therefore not covered by ZDR. For example, Anthropic requires data retention for [Claude Fable 5](/agent-platform/inference/model-choice/#anthropic). For Enterprise teams, these models are **off by default**; a workspace admin must explicitly enable them in the [Admin Panel](/enterprise/team-management/admin-panel/#models). +Some models carry provider-specific data retention requirements and are therefore not covered by ZDR. For Enterprise teams, these models are **off by default**; a workspace admin must explicitly enable them in the [Admin Panel](/enterprise/team-management/admin-panel/#models-settings). Enterprise subscriptions also include: diff --git a/src/content/docs/enterprise/team-management/admin-panel.mdx b/src/content/docs/enterprise/team-management/admin-panel.mdx index b3c6d6f3..41c6dfe7 100644 --- a/src/content/docs/enterprise/team-management/admin-panel.mdx +++ b/src/content/docs/enterprise/team-management/admin-panel.mdx @@ -211,13 +211,13 @@ When enabled, agents understand your code patterns, architecture, and convention * Up to 200,000 files per repository * Team-wide indexing with centralized configuration -### Models +### Models settings Control which LLM models are available to your team and how inference is routed. From the **Models** page, admins can enable or disable individual models and configure [Bring Your Own LLM (BYOLLM)](/enterprise/enterprise-features/bring-your-own-llm/) routing through AWS Bedrock. **Models with provider-specific data retention requirements** -Some models require data retention from the model provider and are therefore not available under [Zero Data Retention (ZDR)](/enterprise/security-and-compliance/security-overview/#zero-data-retention-zdr). For Enterprise teams, these models are **disabled by default**. A workspace admin must explicitly enable them before team members can use them. For example, [Claude Fable 5](/agent-platform/inference/model-choice/#anthropic) requires data retention. +Some models require data retention from the model provider and are therefore not available under [Zero Data Retention (ZDR)](/enterprise/security-and-compliance/security-overview/#zero-data-retention-zdr). For Enterprise teams, these models are **disabled by default**. A workspace admin must explicitly enable them before team members can use them. ### Billing settings diff --git a/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx b/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx index 218c7aba..6a1b7846 100644 --- a/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx +++ b/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx @@ -253,7 +253,7 @@ Zero Data Retention (ZDR) can be enabled in two ways: To discuss organization-wide ZDR for your team, [contact our sales team](https://www.warp.dev/contact-sales). -Regardless of plan, Warp never allows OpenAI, Anthropic, Google, or other model providers to store, retain, or train their models on your data — see [Does Warp have Zero Data Retention policies with LLM providers?](#does-warp-have-zero-data-retention-policies-with-llm-providers) for details. A small number of models are an exception where the provider requires data retention for safety, abuse monitoring, or compliance reasons (for example, [Claude Fable 5](/agent-platform/inference/model-choice/#anthropic)); these are clearly identified and, for Enterprise teams, off by default. +Regardless of plan, Warp never allows OpenAI, Anthropic, Google, or other model providers to store, retain, or train their models on your data — see [Does Warp have Zero Data Retention policies with LLM providers?](#does-warp-have-zero-data-retention-policies-with-llm-providers) for details. ### Can I bring my own API key?