--- title: Models description: >- Explore foundational AI models in Clear Ideas. Learn about model types, capabilities, intelligent selection, and optimal AI performance for different tasks. ogTitle: AI Models Guide ogDescription: >- Explore foundational AI models in Clear Ideas. Learn about reasoning vs conversational models, intelligent selection, and model capabilities ogImage: /assets/images/og/ai-models.webp navigation: icon: fasl fa-sparkles --- # Foundational Models Clear Ideas integrates state-of-the-art language models from leading AI providers including **OpenAI**, **Anthropic**, **Google**, **Cohere**, and **xAI**. These foundational models power all AI features within the platform, enabling everything from conversational chat to complex multi-step workflows. ## Model Architecture Overview Foundational models are large language models trained on extensive datasets to understand and generate human-like text. Clear Ideas provides access to multiple model families, each optimized for different use cases: - **Conversational Models**: Designed for natural dialogue, quick responses, and interactive experiences - **Reasoning Models**: Built for complex analysis, problem-solving, and structured thinking - **Specialized Models**: Optimized for specific domains like coding, data analysis, or creative writing The platform includes both cloud-hosted models from major providers and high-performance models hosted on **Groq's** optimized inference infrastructure, ensuring fast response times and cost efficiency. ## Supported Models ### Foundational Models | Model | Provider | Access | Image Model | Input Credits / 1M | Output Credits / 1M | Image Credits / image | Tags | Description | | --- | --- | --- | --- | ---: | ---: | ---: | --- | --- | | Intelligent | Clear Ideas | All users | No | Variable | Variable | | Recommended | Selects the most appropriate model for the task based on task type, reasoning level required, desired response length, target audience, creativity needs, and time sensitivity. Optimizes for cost efficiency when capabilities are equal. | | GPT-5.4 | OpenAI | All users | No | 2.50 | 15.00 | | Recommended | OpenAI's next-generation flagship model with enhanced capabilities. GPT-5.4 offers superior reasoning, creativity, and factual accuracy across a wide range of complex tasks. Best for demanding professional use cases requiring the most advanced AI capabilities available. | | GPT-5.3-Codex | OpenAI | All users | No | 1.75 | 14.00 | | | OpenAI's most capable agentic coding model for instruction following in technical environments. GPT-5.3-Codex works especially well for implementation-heavy workflow steps like code changes, technical setup, structured troubleshooting, and multi-step engineering tasks. | | GPT-5.4-mini | OpenAI | All users | No | 0.75 | 4.50 | | Recommended | OpenAI's strongest mini model yet for coding, computer use, and subagents. GPT-5.4-mini is optimized for fast, capable everyday work when you want strong reasoning and lower cost than the flagship GPT-5.4. | | GPT-5.4-nano | OpenAI | All users | No | 0.20 | 1.25 | | | OpenAI's cheapest GPT-5.4-class model for simple high-volume tasks. GPT-5.4-nano is designed for speed- and cost-sensitive workloads like classification, data extraction, ranking, and sub-agents. | | GPT-5.4 pro | OpenAI | Subscribers only | No | 21.00 | 168.00 | | High Reasoning, Pro | OpenAI's highest-performance reasoning model with maximum reasoning effort. GPT-5.4 pro offers unparalleled depth and accuracy for the most complex analytical and creative tasks. | | GPT-Image 2 | OpenAI | All users | Yes | 5.00 | 10.00 | 0.034 | Image Generation | OpenAI's state-of-the-art image generation model for fast, high-quality image generation and editing. GPT-Image 2 supports flexible image sizes, high-fidelity image inputs, and stronger image editing workflows. | | XAI Grok 4.20 | xAI | Subscribers only | No | 2.00 | 6.00 | | Recommended | XAI Grok 4.20 is xAI's latest flagship reasoning model with industry-leading speed, strict prompt adherence, agentic tool calling capabilities, and a 2M-token context window for complex workflows. | | XAI Grok 4.1 Fast Reasoning | xAI | Subscribers only | No | 0.20 | 0.50 | | Recommended | XAI Grok 4.1 Fast Reasoning. A high-performance variant of Grok 4.1 optimized for speed with enhanced reasoning capabilities. | | XAI Grok 4.1 Fast Non-Reasoning | xAI | All users | No | 0.20 | 0.50 | | Recommended | XAI Grok 4.1 Fast Non-Reasoning. A high-performance variant of Grok 4.1 optimized for speed without reasoning capabilities. | | XAI Grok Code Fast 1 | xAI | Subscribers only | No | 0.20 | 1.50 | | | XAI Grok Code Fast 1. Specialized model optimized for coding tasks with exceptional performance in software development and technical implementation. | | XAI Grok Imagine Image | xAI | Subscribers only | Yes | 0.002 | 0.02 | 0.02 | Image Generation | XAI Grok Imagine Image is an image generation model for high-quality creative visuals and edits, optimized for fast image output with optional input image guidance. | | XAI Grok Imagine Image Pro | xAI | Subscribers only | Yes | Variable | 0.07 | 0.07 | Image Generation, Pro | XAI Grok Imagine Image Pro is a premium image generation model optimized for higher-fidelity results in creative and marketing workflows. | | Gemini 3 Pro | google | Subscribers only | No | 2.00 | 12.00 | | Recommended | Gemini 3 Pro is the latest generation of Gemini models, offering exceptional reasoning capabilities and large context windows for complex text-based tasks. | | Gemini 3 Flash Preview | google | All users | No | 0.50 | 3.00 | | | Our most intelligent model built for speed, combining frontier intelligence with superior search and grounding. | | Gemini 3 Pro Image Preview | google | Subscribers only | Yes | 2.00 | 0.134 | | Image Generation | Gemini 3 Pro Image, or Gemini 3 Pro (with Nano Banana), is designed to tackle the most challenging image generation by incorporating state-of-the-art reasoning capabilities. It's the best model for complex and multi-turn image generation and editing, having improved accuracy and enhanced image quality. | | Claude 4.6 Sonnet | Anthropic | All users | No | 3.00 | 15.00 | | Recommended | Claude Sonnet 4.6 is an advanced model in the Claude 4 family, offering enhanced capabilities for complex reasoning tasks. | | Claude 4.6 Sonnet | Anthropic | Subscribers only | No | 3.00 | 15.00 | | High Reasoning | Claude Sonnet 4.6 is an advanced model in the Claude 4 family with enhanced reasoning capabilities. | | Claude 4.7 Opus | Anthropic | Subscribers only | No | 5.00 | 25.00 | | Pro | Claude Opus 4.7 is Anthropic's most capable generally available model, with a step-change improvement in agentic coding over Claude Opus 4.6. | | Claude 4.7 Opus | Anthropic | Subscribers only | No | 5.00 | 25.00 | | High Reasoning, Pro | Claude Opus 4.7 is Anthropic's most capable generally available model with strong reasoning for complex analysis and agentic coding. | | Claude 4.5 Haiku | Anthropic | All users | No | 1.00 | 5.00 | | Recommended | Claude Haiku 4.5 is a fast and efficient model in the Claude 4 family, optimized for speed and cost-effectiveness. | | Claude 4.5 Haiku | Anthropic | Subscribers only | No | 1.00 | 5.00 | | High Reasoning | Claude Haiku 4.5 is a fast and efficient model in the Claude 4 family with enhanced reasoning capabilities. | | GPT-OSS 20B | OpenAI | All users | No | 0.10 | 0.50 | | | GPT-OSS 20B is OpenAI's flagship open source model, built on a Mixture-of-Experts (MoE) architecture with 20 billion parameters and 32 experts. Hosted by Groq. | | GPT-OSS 120B | OpenAI | All users | No | 0.15 | 0.75 | | Recommended | GPT-OSS 120B is OpenAI's flagship open source model, built on a Mixture-of-Experts (MoE) architecture with 120 billion parameters and 128 experts. Hosted by Groq. | | Command A | Cohere | Subscribers only | No | 2.50 | 10.00 | | | Cohere's Command A is a sophisticated large language model designed to assist users by providing thorough, accurate, and contextually relevant responses. | The models table identifies image-capable models and includes per-image output pricing where applicable. ## 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, such as OpenAI's GPT-5 Pro and Anthropic's Claude Opus series, allocate more computational resources to deliberate processing, resulting in higher accuracy for complex tasks but potentially longer response times. **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 Models like GPT-5 Mini and Claude Haiku are optimized for conversational flow, making them ideal for chat interfaces and time-sensitive interactions where responsiveness is critical. ### Specialized and High-Performance Models Beyond general-purpose models, Clear Ideas offers specialized options: **Code-Optimized Models**: xAI's Grok Code Fast 1 specializes in programming tasks, offering superior performance for software development, debugging, and technical implementation. **Groq-Hosted Models**: Select OpenAI models are hosted on Groq's advanced inference infrastructure, providing exceptional speed and efficiency. These include GPT-OSS variants that deliver enterprise-grade performance with optimized latency. **Multimodal Models**: Google's Gemini series integrates text, vision, and multimodal understanding, enabling more comprehensive analysis of diverse content types. ## 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** (summarization, basic Q&A): Conversational models like GPT-5 Nano or Claude Haiku provide fast, cost-effective results - **Complex Analysis** (research, technical problem-solving): Reasoning models like GPT-5 Pro or Claude Opus deliver deeper analysis and higher accuracy ### 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**: Specialized models like Grok Code Fast 1 provide superior programming assistance - **Multimodal Data**: Google's Gemini series handles diverse content types including images and documents - **Enterprise Scale**: High-performance hosted models ensure consistent performance under load ### Image Inputs in Workflows For AI Workflows, 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.