gpt-5-2025-08-07.description

GPT-5 mini is a faster, more cost-efficient version of GPT-5. Great for well-defined tasks and precise prompts with high reasoning capabilities.

GPT-5 nano is our fastest, cheapest version of GPT-5. Great for summarization and classification tasks with average reasoning capabilities.

0.description

Grok 3 Mini Beta model, supports reasoning trace via reasoning_content field.

XAI latest and greatest flagship model, offering unparalleled performance in natural language, math and reasoning - the perfect jack of all trades.

grok-4-fast-non-reasoning.description

grok-4-fast-reasoning.description

Gemini 2.5 Pro is Google's latest multimodal AI model, offering advanced reasoning capabilities and efficient handling of complex tasks. It supports multimodal generation, enabling seamless integration of text, images, and other inputs for more powerful and flexible AI interactions.

Gemini 2.5 Flash is a lightweight, high-speed AI model from Google, optimized for fast, efficient performance in tasks like chat, summarization, and multimodal understanding.

Gemini 2.5 Flash (Thinking Mode) is Google’s fast, lightweight AI model with enhanced reasoning for complex tasks. It supports long context, multimodal input, and native tool use, balancing speed and intelligence.

Gemini 1.5 Pro supports up to 2 million tokens, making it an ideal choice for medium-sized multimodal models, providing multifaceted support for complex tasks.

Mistral Small is a cost-effective, fast, and reliable option suitable for use cases such as translation, summarization, and sentiment analysis.

Mistral Medium 3 is a frontier-class multimodal model released on May 2025. It is termed the new large and has a context window of 128k tokens. Mistral Medium 3 delivers state-of-the-art performance at 8X lower cost with radically simplified enterprise deployments.

The Pixtral model demonstrates strong capabilities in tasks such as chart and image understanding, document question answering, multimodal reasoning, and instruction following. It can ingest images at natural resolutions and aspect ratios and handle an arbitrary number of images within a long context window of up to 128K tokens.

Tongyi Qianwen Plus is an enhanced version of the large-scale language model, supporting input in various languages, including Chinese and English.

0.description

0.description

0.description

Tongyi Qianwen Max is a large-scale language model with hundreds of billions of parameters, supporting input in various languages, including Chinese and English. It is the API model behind the current Tongyi Qianwen 2.5 product version.

A new open-source model that integrates general and coding capabilities, retaining the general conversational abilities of the original Chat model and the powerful code handling capabilities of the Coder model, while better aligning with human preferences. Additionally, DeepSeek-V2.5 has achieved significant improvements in writing tasks, instruction following, and more.

R1 is the reasoning model launched by DeepSeek. Before outputting the final answer, the model first provides a chain of thought to enhance the accuracy of the final response.

Sonar Reasoning Pro is a high-performance AI model designed for complex, multi-step reasoning across text and visual inputs. Optimized for analytical depth, it supports long-context processing and excels in domains like research, strategy, and technical problem-solving.

Sonar Reasoning is an advanced AI model built for deep logical analysis and structured thinking. It handles complex tasks with precision, supports long-form context, and is ideal for applications in education, decision support, and scientific research.

Sonar Pro is an advanced search and reasoning model from Perplexity, designed to deliver accurate, context-aware answers by integrating real-time web search with multi-turn query handling. It supports complex queries, follow-up questions, and deep retrieval tasks, making it ideal for research, enterprise search, and professional decision-making.