Models

Clear Ideas uses a managed model catalog to power governed AI features across the workspace, from conversational chat to multi-step Agent runs. The catalog can include provider-hosted models, Clear Ideas aliases, Private Models, image-capable models, and models with specialized capabilities such as structured outputs or file-generation skills.

Model Architecture Overview

Models are selected for different workloads. Clear Ideas exposes the essential information needed to choose safely:

• Provider: where the model runs or how it is managed
• Access: whether the model is available to all users, subscribers, or Private Model lanes
• Reasoning: whether the model supports reasoning effort controls
• Structured outputs: whether the model can reliably produce schema-shaped output
• Image and file generation support: whether the model can support generated images or file-generation skills
• AI Credits: the current credit cost where applicable

Because model availability changes over time, the table below is loaded from the Clear Ideas model catalog rather than maintained as static documentation.

Supported Models

The models table identifies image-capable models and includes per-image output pricing where applicable.

Model Lanes

Clear Ideas model choices can include several lanes:

• Private Models for sensitive, bounded, or repeatable work where private execution and cost predictability matter.
• Provider Models for premium reasoning, broad multimodal capability, specialized model behavior, or a specific external provider model approved by policy.
• Intelligent selection when you want Clear Ideas to choose an appropriate approved model for the task.

See Private Models and Model Policy.

Model and Reasoning Selector

Clear Ideas uses one model selector for model choice and reasoning effort. Choose Intelligent when you want Clear Ideas to pick the best model for the task, or choose a specific model when you need predictable behavior, pricing, or capability support.

The reasoning setting controls how much deliberate reasoning budget the model should use:

• Auto uses Clear Ideas' default behavior for the selected model and provider. It is recommended for most work.
• Low favors speed and lower cost.
• Medium balances speed and depth.
• High and Extra High spend more reasoning budget for difficult analysis, planning, coding, or synthesis.

Auto often behaves like a balanced medium setting on current reasoning-capable models, but it is not a fixed medium override. It means Clear Ideas does not force a specific effort level unless the selected model or Agent requires one.

AI Chat uses concrete model choices because chat runs immediately. Agents can also offer latest aliases so future scheduled runs can follow the current production model. Choose a concrete model version when repeatability matters more than automatic upgrades.

Organization model policy can allow all models, Private Models, Provider Models, latest aliases, or specific concrete models. Deprecated models may remain visible only when they already exist in policy or older Agent definitions so administrators can remove or replace them deliberately. Deprecated models are not automatically replaced by successors at execution time. If an Agent or run references a deprecated or no-longer-permitted model, update it to an active permitted model before running it.

Model Capabilities and Selection

Reasoning vs. Conversational Models

Clear Ideas provides models optimized for different interaction patterns and cognitive workloads. Understanding these distinctions helps in selecting the most effective model for your specific use case.

Reasoning Models excel at structured thinking and complex problem-solving:

• Multi-step analysis and logical deduction
• Technical problem-solving and code generation
• Mathematical computations and data analysis
• Research synthesis and detailed explanations

These models allocate more computational resources to deliberate processing, resulting in higher accuracy for complex tasks but potentially longer response times and higher credit usage.

Conversational Models prioritize natural interaction and rapid responses:

• Natural dialogue and contextual understanding
• Quick Q&A and information retrieval
• Interactive brainstorming and ideation
• Concise summaries and explanations

Conversational models are optimized for flow and responsiveness, making them useful for chat interfaces and time-sensitive interactions where speed matters.

Specialized and High-Performance Models

Beyond general-purpose models, the catalog can include specialized options:

Code-Optimized Models: Some models are better suited for software, structured transformation, debugging, and technical implementation tasks.

High-Throughput Models: Some models or providers prioritize latency and throughput for faster responses.

Multimodal Models: Some models support image or multimodal understanding, enabling analysis across more than plain text.

Intelligent Model Selection

Clear Ideas features an Intelligent model selector that automatically optimizes model choice based on contextual analysis. The system evaluates:

• Task Complexity: Determines reasoning depth requirements and selects appropriate model capabilities
• Content Type: Adapts to text, code, data analysis, or multimodal content
• Response Parameters: Considers desired length, detail level, and output format
• Performance Constraints: Balances speed, cost, and accuracy based on user preferences
• Cost Optimization: When multiple models are viable, prioritizes the most cost-effective option

This intelligent routing ensures optimal performance without requiring manual model selection for most use cases.

Model Selection Considerations

While the Intelligent selector handles most scenarios, understanding key factors can help you make informed choices for specialized requirements:

Task Complexity

• Simple Tasks such as summarization and basic Q&A usually benefit from faster, lower-cost models.
• Complex Analysis such as research synthesis, technical problem-solving, and multi-document comparison usually benefits from stronger reasoning models.

Response Characteristics

• Concise Output: Faster models optimize for brevity and quick responses
• Detailed/Exhaustive: Reasoning-focused models excel at comprehensive explanations and multi-step analysis

Performance Requirements

• Speed-Critical: Groq-hosted models and lightweight variants prioritize low latency
• Quality-Critical: Flagship models from each provider offer maximum capability for demanding applications

Content Type

• Code/Technical: Choose models with strong structured reasoning and coding support.
• Multimodal Data: Choose models that support the needed media or image capabilities.
• Enterprise Scale: Use policy-approved models that balance reliability, cost, and performance for the expected workload.

File Generation Skills

Some models support file generation skills for spreadsheets, documents, and presentations. These skills require the model to follow specialized instructions, inspect source file structure when needed, call tools, and write Python code that produces the requested file.

File helpers only appear when the selected model supports skills. Stronger reasoning and coding-capable models are usually better for complex workbooks, polished documents, and presentation decks. Simpler models may still generate basic files, but output quality and repair reliability can vary.

See File Generation in Chat and Agents.

Image Inputs in Agents

For Agents, there are two different image input paths:

• Inline {{imageRefVariable}} in prompt content uses OCR/extracted text context
• Prompt image attachments (selected imageRef variables) send actual image binaries to the model

Choose a vision-capable multimodal model when using prompt image attachments. Inline image references remain text-based and do not require vision input support.

Related Documentation

• Private Models
• Model Policy
• AI Settings
• AI Credits
• Agent Runs