Model Support and Deprecation

This page tracks the lifecycle status and support for generative AI models used by Appian. It provides information about currently supported models, regional availability, deprecation timelines, and guidance for administrators managing AI model configurations.

As models are added, updated, or deprecated, use this page to:

• Understand which models are currently supported.
• Plan for model deprecations and transitions.
• Identify regional restrictions that may impact feature availability.
• Take required administrative actions to maintain AI functionality.

Use the interactive tool below to explore which models power each feature, view their processing regions, and understand which regions your data may be processed in:

Supported models

The following models are currently supported in Appian:

Model	Availability	Notes
Claude Sonnet 5	Requires inference profile	Latest Sonnet reasoning model
Claude Sonnet 4.6	Requires inference profile	Reasoning model with larger context window
Amazon Nova 2 Lite	Requires inference profile	Fast model for text and vision tasks; not available for GovCloud
Claude Sonnet 4.5	Requires inference profile	Smartest model for complex AI agents and coding
Claude Sonnet 4	Requires inference profile	High intelligence and balanced performance
Claude Haiku 4.5	Requires inference profile	Fastest model with near-frontier intelligence
Claude Sonnet 3.7	Requires inference profile	High-performance model with improved reasoning
Claude Sonnet 3.5 v2	Limited regions	Updated version with improved capabilities
Claude Haiku 3.5	Limited regions	Fast, efficient language model
Claude Sonnet 3	Limited regions	Balance of intelligence and speed
Claude Haiku 3	Multiple regions	Quick and accurate targeted performance
GPT 5.4 (Appian)	Limited regions	Latest flagship model with cutting-edge reasoning capabilities; extended thinking always enabled
GPT 5.5 (Appian)	Limited regions	Most capable model with advanced reasoning and multimodal understanding; extended thinking always enabled
GPT 5.4 (BYO AWS)	Limited regions	Latest flagship model with cutting-edge reasoning capabilities; extended thinking always enabled
GPT 5.5 (BYO AWS)	Limited regions	Most capable model with advanced reasoning and multimodal understanding; extended thinking always enabled
GPT 5.4	Customer Azure deployment	Latest flagship model with cutting-edge reasoning capabilities
GPT 5.4 Pro	Customer Azure deployment	Premium model with extended thinking for the most demanding tasks
GPT 5.4 mini	Customer Azure deployment	Fast and efficient GPT-5.4 variant for everyday tasks
GPT 5.4 nano	Customer Azure deployment	Smallest and cheapest GPT-5.4 variant for speed
GPT 5.3 codex	Customer Azure deployment	Latest code-specialized model with state-of-the-art coding performance
GPT 5.2	Customer Azure deployment	Enhanced flagship model with improved performance across tasks; supports disablable extended thinking
GPT 5.2 codex	Customer Azure deployment	Code-specialized model for advanced software development workflows
GPT 5.1	Customer Azure deployment	Improved flagship model with enhanced reasoning and multimodal support; supports disablable extended thinking
GPT 5.1 codex max	Customer Azure deployment	Maximum compute code model with extended thinking for complex engineering
GPT 5.1 codex	Customer Azure deployment	Code-specialized model with improved software engineering capabilities; supports disablable extended thinking
GPT 5 Pro	Customer Azure deployment	Premium reasoning model with extended thinking for complex tasks
GPT 5	Customer Azure deployment	GPT reasoning model
GPT 5 codex	Customer Azure deployment	Code-specialized model optimized for software engineering tasks
GPT 5 mini	Customer Azure deployment	Fast and efficient model balancing speed and capability
GPT 5 nano	Customer Azure deployment	Smallest and fastest GPT-5 variant for low-latency tasks
GPT 4o	Customer Azure deployment	Multimodal model with vision and audio capabilities; supports disablable extended thinking
GPT 4o mini	Customer Azure deployment	Compact multimodal model balancing speed and capability
GPT 4.1	Customer Azure deployment	Flagship model for complex reasoning and coding
GPT 4.1 mini	Customer Azure deployment	Fast and efficient for everyday tasks; does not support extended thinking
Amazon Textract	Multiple regions	Document analysis and text extraction
Titan Text Embeddings V2	Multiple regions	Text embedding for semantic search

PDF processing

The PDF limits for "Visual elements & text" document processing mode vary by model:

Model	Max pages	Max file size
Claude Sonnet 5	100	24 MB
Claude Sonnet 4.6	100	24 MB
Claude Sonnet 4	100	24 MB
Claude Sonnet 4.5	100	24 MB
Claude Haiku 4.5	100	24 MB
Amazon Nova 2 Lite	100	18 MB
All Azure OpenAI GPT models	100	24 MB
All Appian GPT models	100	24 MB
Claude Sonnet 3.5 (legacy)	20	25 MB
Claude Sonnet 3.7 (legacy)	20	25 MB

Administrators can also disable all models from a provider at the environment level to prevent Appian from routing requests to that provider.

Region-restricted models

Some models are not supported in all regions. Feature availability depends on whether the model's selected inference profile includes a region where the model is supported.

To ensure your AI features continue to work as expected, make sure your environment uses a model that supports the inference profile for the region where your data is processed. Review your inference profile configuration in the Administration Console under AI Services.

Deprecated models

The following models have been deprecated.

Model	Deprecation date	Replacement	Impacted regions
Claude Sonnet 4	October 14, 2026	Latest available Sonnet model	All regions where this model is offered
Claude Haiku 3	September 10, 2026		ap-northeast-1 (Tokyo) ap-southeast-2 (Sydney) eu-central-1 (Frankfurt) eu-west-1 (Ireland) eu-west-2 (London) eu-west-3 (Paris) us-east-1 (N. Virginia) us-west-2 (Oregon) us-gov-west-1 (GovCloud) us-gov-east-1 (GovCloud)
Claude Sonnet 3 v1	July 30, 2026	Latest available Sonnet model	ap-northeast-1 (Tokyo) ap-northeast-2 (Seoul) ap-southeast-2 (Sydney) eu-west-1 (Ireland) eu-west-3 (Paris) us-east-1 (N. Virginia) us-west-2 (Oregon)
Claude Sonnet 3.5 v1	July 30, 2026	Latest available Sonnet model	us-gov-west-1 (GovCloud) us-gov-east-1 (GovCloud) ap-northeast-1 (Tokyo) ap-northeast-2 (Seoul) ap-southeast-1 (Singapore) ap-southeast-2 (Sydney)
Claude Sonnet 3.5 v1	June 1, 2026	Latest available Sonnet model	eu-central-2 (Zurich)
Claude Sonnet 3.5 v1	March 1, 2026	Latest available Sonnet model	us-east-1 (N. Virginia) us-west-2 (Oregon) eu-central-1 (Frankfurt) eu-central-2 (Zurich)

What happens when a model is deprecated

When a model is deprecated:

• AI Skills: Existing AI Skills using the deprecated model will continue to function until the model is fully removed. You will receive advance notice to update your skills to use a replacement model.
• Required Actions: Administrators must update all AI Skills and agents to use replacement models before the deprecation deadline to avoid service disruptions.
• Regional Implications: If a replacement model has different regional availability than the deprecated model, you may need to adjust your inference profile configuration.

Upcoming model deprecations

Models are periodically deprecated by their respective providers, such as Anthropic and AWS. When this happens, Appian updates the models that are available to ensure the best performance, security, and compliance. Older models may be deprecated as part of this lifecycle. We communicate these changes to help you plan ahead.

The following table lists upcoming model deprecations.

Model	Deprecation date	Impacted regions
Claude Sonnet 4.5	April 8, 2027	All regions where this model is offered
Claude Haiku 3	November 13, 2026	ap-northeast-2 (Seoul) ap-south-1 (Mumbai) ap-southeast-1 (Singapore) eu-central-2 (Zurich) sa-east-1 (São Paulo) ca-central-1 (Canada)
Claude Sonnet 3	November 13, 2026	ap-south-1 (Mumbai) ap-southeast-1 (Singapore) eu-west-2 (London) sa-east-1 (São Paulo)
Claude Sonnet 3.5 v1 & v2	November 13, 2026	ap-northeast-2 (Seoul) ap-south-1 (Mumbai) ap-southeast-1 (Singapore)
Claude Sonnet 3.7	November 13, 2026	ap-south-1 (Mumbai) eu-west-2 (London)

Prepare for model deprecations

To ensure smooth operation of AI features and prepare for model changes:

• Verify enabled models in the Administration Console under AI Services.
• Review inference profiles to ensure they include regions that support your required models.
• Check feature availability in the Regional Availability page.
• Monitor deprecation timelines on this page and plan updates accordingly.
• Test AI Skills and agents after making any model or inference profile changes.
• Review release notes to stay informed about model updates and deprecations.

For more information about AI model configuration and availability, see the following pages:

• For configuration, see AI Services.
• For regional availability and inference profiles, see Regional Availability.
• For data processing and encryption details, see Security & Compliance.

Feedback