DocumentationModels

Models

In anymize you choose between AI models from several makers, and this page shows for each one where it runs, what the provider does with your requests and what it can do.

5 min readUpdated

What the model choice means

With anonymization on, anymize replaces names, addresses, file numbers and other personal data with placeholders before any model sees the text. That applies to every model on this page. The model choice decides the tool, not the protection.

Smart Select picks a fitting model for each request from the models you may use. You can also pick one model in chat and stick with it.

This list is the model catalog admins see under Governance > Models. anymize's own models (Waterfall, Fountain) are not in it, because every account has them without a choice of provider. Self-connected models (BYOM) are not in it either.

Hosting: EU or international

Every model has a jurisdiction. An EU model runs in data centres in the EU. An international model runs at the maker or an operator in the USA.

Many models are available from several operators, for example Google Cloud (Vertex AI) and AWS Bedrock. For each request anymize picks the operator with the best availability, but only within the model's jurisdiction. An EU model never falls back to an operator outside the EU. If everything in the jurisdiction is down, the model is briefly unavailable instead of running somewhere else.

Some models exist in both jurisdictions. The international version then carries (USA) in its name.

All models at a glance

ModelMakerHostingData retention at the providerContext windowInputsCapabilitiesClass
Qwen3 235BAlibabaEUNone (ZDR)128,000TextTools, ReasoningSwift
Qwen3 32BAlibabaEUNone (ZDR)not statednot statednot statedSwift
Qwen3 Next 80B ThinkingAlibabaEUNone (ZDR)not statednot statednot statedSwift
Claude 4.5 HaikuAnthropicEUNone (ZDR)200,000Text, ImagesTools, ReasoningSwift
Claude 4.5 OpusAnthropicUSANone (ZDR)200,000Text, ImagesTools, ReasoningDeep
Claude Fable 5AnthropicUSA30 days1,000,000Text, ImagesTools, ReasoningUltra
Claude Fable 5.1AnthropicUSA30 days1,000,000Text, ImagesTools, ReasoningUltra
Claude Fable 5.2AnthropicUSA30 days1,000,000Text, ImagesTools, ReasoningUltra
Claude Haiku 5.5AnthropicEUNone (ZDR)1,000,000Text, ImagesTools, ReasoningSwift
Claude Haiku 5.5 (USA)AnthropicUSANone (ZDR)1,000,000Text, ImagesTools, ReasoningSwift
Claude Opus 4.8AnthropicEUNone (ZDR)1,000,000Text, ImagesTools, ReasoningDeep
Claude Opus 5AnthropicUSANone (ZDR)1,000,000Text, ImagesTools, ReasoningDeep
Claude Opus 5.5AnthropicEUNone (ZDR)1,000,000Text, ImagesTools, ReasoningDeep
Claude Opus 5.5 (USA)AnthropicUSANone (ZDR)1,000,000Text, ImagesTools, ReasoningDeep
Claude Sonnet 4.5AnthropicUSANone (ZDR)not statednot statednot statedSmart
Claude Sonnet 4.6AnthropicEUNone (ZDR)1,000,000Text, ImagesTools, ReasoningSmart
Claude Sonnet 5AnthropicUSANone (ZDR)1,000,000Text, ImagesTools, ReasoningSmart
Claude Sonnet 5.5AnthropicEUNone (ZDR)1,000,000Text, ImagesTools, ReasoningSmart
Claude Sonnet 5.5 (USA)AnthropicUSANone (ZDR)1,000,000Text, ImagesTools, ReasoningSmart
DeepSeek V4.1 FlashDeepSeekEUNone (ZDR)1,000,000Text, ImagesTools, ReasoningSwift
DeepSeek-V3-0324DeepSeekUSANone (ZDR)not statednot statednot statedSmart
Gemini 2.5 FlashGoogleUSANone (ZDR)1,048,576Text, ImagesToolsSwift
Gemini 2.5 ProGoogleEUNone (ZDR)1,048,576Text, ImagesTools, ReasoningDeep
Gemini 3.0 FlashGoogleUSANone (ZDR)1,048,576Text, ImagesTools, ReasoningSmart
Gemini 3.1 Flash-LiteGoogleEUNone (ZDR)1,048,576Text, ImagesTools, ReasoningSwift
Gemini 3.5 FlashGoogleEUNone (ZDR)1,048,576Text, ImagesTools, ReasoningSmart
Gemini 3.5 Flash-LiteGoogleEUNone (ZDR)1,048,576Text, ImagesTools, ReasoningSwift
Gemini 3.8 FlashGoogleEUNone (ZDR)1,048,576Text, ImagesTools, ReasoningSmart
Gemini 3.8 Flash (USA)GoogleUSANone (ZDR)1,048,576Text, ImagesTools, ReasoningSmart
Gemini 4 ArgonGoogleEUNone (ZDR)1,048,576Text, ImagesTools, ReasoningDeep
Gemini 4 CarbonGoogleEUNone (ZDR)1,048,576Text, ImagesTools, ReasoningDeep
Gemma 3 27BGoogleEUNone (ZDR)128,000TextTools, ReasoningSwift
MiniMax M2.5MiniMaxEUNone (ZDR)128,000TextTools, ReasoningSwift
Mistral Large 4MistralEUNone (ZDR)524,288Text, ImagesTools, ReasoningSmart
Mistral Medium 3.5MistralEUNone (ZDR)not statednot statednot statedSmart
Mistral SmallMistralEUNone (ZDR)256,000Text, ImagesTools, ReasoningSwift
Kimi K2.6Moonshot AIUSANone (ZDR)not statednot statednot statedDeep
Kimi K3Moonshot AIEUNone (ZDR)1,048,576TextTools, ReasoningDeep
Nemotron 3 Nano OmniNVIDIAEUNone (ZDR)not statednot statednot statedSwift
GPT 5.5OpenAIEUNone (ZDR)1,050,000Text, ImagesTools, ReasoningDeep
GPT 5.6 LunaOpenAIUSANone (ZDR)1,050,000Text, ImagesTools, ReasoningSmart
GPT 5.6 SolOpenAIUSANone (ZDR)1,050,000Text, ImagesTools, ReasoningUltra
GPT 5.6 TerraOpenAIEUNone (ZDR)1,050,000Text, ImagesTools, ReasoningDeep
GPT 5.6 Terra (USA)OpenAIUSANone (ZDR)1,050,000Text, ImagesTools, ReasoningDeep
GPT-5OpenAIUSANone (ZDR)400,000Text, ImagesTools, ReasoningSmart
GPT-5 MiniOpenAIEUNone (ZDR)200,000TextTools, ReasoningSwift
GPT-5.4OpenAIEUNone (ZDR)1,050,000Text, ImagesTools, ReasoningSmart
GPT-6 AstraOpenAIUSANone (ZDR)1,050,000Text, ImagesTools, ReasoningUltra
GPT-6 LunaOpenAIEUNone (ZDR)1,050,000Text, ImagesTools, ReasoningSwift
GPT-6 Luna (USA)OpenAIUSANone (ZDR)1,050,000Text, ImagesTools, ReasoningSwift
GPT-6 SolOpenAIUSANone (ZDR)1,050,000Text, ImagesTools, ReasoningDeep
GPT-6.1 SolOpenAIEUNone (ZDR)1,050,000Text, ImagesTools, ReasoningDeep
GPT-6.1 Sol (USA)OpenAIUSANone (ZDR)1,050,000Text, ImagesTools, ReasoningDeep
GPT-6.1 TerraOpenAIEUNone (ZDR)1,050,000Text, ImagesTools, ReasoningDeep
GPT-6.1 Terra (USA)OpenAIUSANone (ZDR)1,050,000Text, ImagesTools, ReasoningDeep
Perplexity ProPerplexityUSANone (ZDR)131,072TextWeb search with sourcesSwift
GLM 5.2Z.aiEUNone (ZDR)1,000,000TextTools, ReasoningSmart
GLM 5.3Z.aiEUNone (ZDR)1,000,000TextTools, ReasoningSwift
Grok 4.5xAIUSANone (ZDR)500,000Text, ImagesTools, ReasoningSmart
Grok 4.6xAIUSANone (ZDR)500,000Text, ImagesTools, ReasoningSmart
Grok 4.7xAIUSANone (ZDR)500,000Text, ImagesTools, ReasoningSmart

Context window and maximum output are the operator's figures in tokens. In a chat anymize does not always use the full window and summarizes long histories before it fills up. The class is the usage class from the model picker. Where a cell says “not stated”, we have no verified figure.

Zero data retention

The models in anymize run with zero data retention: the provider does not store prompts or answers, only technical metadata such as time, model and token count. No provider uses the data for training.

The exception is Claude Fable 5, 5.1 and 5.2. For these Anthropic stores prompts and answers for 30 days for abuse detection, and zero data retention is not available for them. With anonymization this only concerns placeholders.

In a team, an admin can block such models with the rule “Only models with zero data retention”. They then show greyed out in the model picker, with the reason next to them.

Retirements

Makers and operators switch older models off at some point. Once an operator has a retirement date, anymize takes it out of routing 7 days before. Your requests then run through the remaining operators in the same jurisdiction, and nobody sees an error on the day.

If no operator is left for a model, it disappears from the picker and its page here is removed.

Alle Seiten in diesem Bereich

Anthropic

Claude 4.5 HaikuClaude 4.5 Haiku is an AI model by Anthropic that runs in anymize in the EU.Claude 4.5 OpusClaude 4.5 Opus is an AI model by Anthropic that runs in anymize internationally (USA).Claude Fable 5Claude Fable 5 is an AI model by Anthropic that runs in anymize internationally (USA).Claude Fable 5.1Claude Fable 5.1 is an AI model by Anthropic that runs in anymize internationally (USA).Claude Fable 5.2Claude Fable 5.2 is an AI model by Anthropic that runs in anymize internationally (USA).Claude Haiku 5.5Claude Haiku 5.5 is an AI model by Anthropic that runs in anymize in the EU.Claude Haiku 5.5 (USA)Claude Haiku 5.5 (USA) is an AI model by Anthropic that runs in anymize internationally (USA).Claude Opus 4.8Claude Opus 4.8 is an AI model by Anthropic that runs in anymize in the EU.Claude Opus 5Claude Opus 5 is an AI model by Anthropic that runs in anymize internationally (USA).Claude Opus 5.5Claude Opus 5.5 is an AI model by Anthropic that runs in anymize in the EU.Claude Opus 5.5 (USA)Claude Opus 5.5 (USA) is an AI model by Anthropic that runs in anymize internationally (USA).Claude Sonnet 4.5Claude Sonnet 4.5 is an AI model by Anthropic that runs in anymize internationally (USA).Claude Sonnet 4.6Claude Sonnet 4.6 is an AI model by Anthropic that runs in anymize in the EU.Claude Sonnet 5Claude Sonnet 5 is an AI model by Anthropic that runs in anymize internationally (USA).Claude Sonnet 5.5Claude Sonnet 5.5 is an AI model by Anthropic that runs in anymize in the EU.Claude Sonnet 5.5 (USA)Claude Sonnet 5.5 (USA) is an AI model by Anthropic that runs in anymize internationally (USA).