Your code is never stored. GDPR-compliant processing with immediate data deletion.
View our security standardsAI Models
Lura, Claude, GPT, and Gemini: pick the right model per task. Processing depends on model and region; customer data is not used for training.
Lurus Code
Hosted in Europe and the US. Zero Data Retention. No Training.Lura
Balancedlura Anthropic
Hosted in Europe. Zero Data Retention. No Training.Claude Opus 4.8
Powerfulopus Claude Opus 4.7
Powerfulopus-4.7 Claude Opus 4.6
Powerfulopus-4.6 Claude Sonnet 4.6
Balancedsonnet Claude Opus 4.5
Powerfulopus-4.5 Claude Sonnet 4.5
Balancedsonnet-4.5 Claude Haiku 4.5
Fasthaiku Gemini 2.5 Pro
Powerfulgemini-pro Gemini 3.5 Flash
Balancedgemini-3.5-flash Gemini 3.1 Flash Lite
Fastgemini OpenAI
Hosted in Europe. Zero Data Retention. No Training.GPT-5.5
Powerfulgpt GPT-5.4 Pro
Powerfulgpt-pro GPT-5.4
Powerfulgpt-5.4 GPT-5.3 Codex
Powerfulgpt-codex GPT-5.1 Codex Max
Powerfulgpt-codex-max o4-mini
Powerfulo4-mini GPT-5.4 Mini
Fastgpt-mini EU-Provider
Hosted in Europe. Zero Data Retention. No Training.GLM 5.1
Powerfulglm Kimi K2.6
Powerfulkimi Qwen3.5 397B
Balancedqwen DeepSeek V3.2
Balanceddeepseek MiniMax M2.5
Balancedminimax GPT OSS 120B
Fastgpt-oss Global Providers
US-hosted. Zero Data Retention. No Training.Global providers are hosted in the US. Your prompts and code are never stored or used for training.
DeepSeek V4 Pro
Powerfuldeepseek-pro MiniMax M2.7
Powerfulminimax-m2.7 Qwen3.6 Plus
Powerfulqwen-plus Kimi K2.6 (Fast)
Powerfulkimi-fast GLM 5.1 (Fast)
Powerfulglm-fast Capabilities, Legend
The tags on each card describe which capabilities that model supports in Lurus Code.
- Tool Calling
Structured tool and function calls, e.g. files, terminal, and integrations.
- Vision
Images and screenshots can be analyzed together with text.
- Adaptive Thinking
Scales reasoning depth dynamically based on task complexity (Claude adaptive thinking).
- Extended Thinking
Extra reasoning time for harder tasks (Claude extended thinking).
- Reasoning
Geared toward deeper multi-step and logical reasoning.
- Prompt Caching
Reuses prompt prefixes for lower latency and cost.
Automatic fallback chains
When a provider is temporarily unavailable, Lurus Code can automatically switch to an alternative model in the configured fallback chain, so your session keeps going without manual switching.
Ready for GDPR-compliant AI?
Get started and use every model GDPR-compliantly in one surface.
Get Started