Skip to main content
Neo supports a range of frontier models from Anthropic, OpenAI, Google, xAI, and others. You can set a preferred model under Settings → Models, and override it per task or per automation. The model you choose applies to the primary reasoning agent. Sub-agents in Thorough mode may use different models optimized for their specific role.

​
Choosing a model

Auto is the default. It selects a cost-effective model with the right intelligence level for each task automatically. For most users, Auto is the right starting point. If you want direct control, select a specific model. Use the descriptions below to match the model to your use case.

​
Available models

​
Anthropic

ModelBest for
Claude Opus 4.8Latest and best for complex security tasks
Claude Opus 4.7Latest and best for complex security tasks
Claude Opus 4.6Slightly less capable than Opus 4.7
Claude Sonnet 4.6Latest Sonnet with adaptive thinking
Claude Haiku 4.5Fast and efficient for quick tasks

​
OpenAI

ModelBest for
GPT-5.5 HighHigh-reasoning GPT model with a 270K context window
GPT-5.4 XHighMaximum reasoning power for critical analysis
GPT-5.4 HighStrong reasoning for deep security analysis
GPT-5.3 Codex HighAdvanced security code review and analysis

​
Google

ModelBest for
Gemini 3.0 ProDeep research tasks
Gemini 3.0 FlashFast and efficient for quick research

​
xAI

ModelBest for
Grok 4.3 HighFrontier reasoning at high effort
Grok 4.3 FastSame model, low reasoning effort for speed

​
Others

ModelBest for
Kimi K2.6Most cost-efficient in reasoning
GLM 5Strong reasoning with large context
GLM 5.1Z.ai flagship with improved agentic reasoning
DeepSeek V4 Pro HighFrontier open reasoning at high effort

​
Overriding the model

You can override the default model for a specific automation in the automation’s Configuration section. This lets you run different automations on different models without changing your global preference.