Nano Banana 2Google

Latest evolution blending Pro capabilities at Flash speed. Ideal for precise creative workflows with world knowledge and text translation. Photorealistic fidelity, real-time search integration, production-ready specs.

Gemini 3.1 ProGoogle

Google's most advanced reasoning model as of February 2026 — featuring unprecedented depth and nuance in complex problem-solving, natively multimodal across text, images, audio, video, and code repositories. With a 1M-token context window and significant upgrades to agentic workflows, software engineering capabilities, and thinking efficiency, it's Google's sharpest tool yet for tasks where a simple answer simply isn't enough.

Gemini 3 FlashGoogle

Google's most intelligent model built for speed, combining frontier intelligence with superior search and grounding.

Nano Banana ProGoogle

The op model for image generation

Nano BananaGoogle

YES, it generates images

Gemini 3 ProGoogle

The best model in the world for multimodal understanding, and google's most powerful agentic and vibe-coding model yet.

Gemini 2.0 Flash LiteGoogle

Google's cheapest model. Similar to 2.0 Flash, but even faster. Not as smart, but still good at most things.

Gemini 2.0 FlashGoogle

Google's flagship model, known for speed and accuracy (and also web search!). Has an insanely large context window.

Gemini 2.5 Flash LiteGoogle

Similar to 2.0 Flash, but even faster. Not as smart, but still good at most things.

Gemini 2.5 FlashGoogle

Google's state of the art fast model, known for speed, accuracy and web search. Not quite as smart as Claude Sonnet, but WAY faster and cheaper.

Gemini 2.5 ProGoogle

Most advanced reasoning Gemini model, capable of solving complex problems.

SonarPerplexity

Perplexity's fast, web-grounded model for everyday question answering with citations.

Sonar ProPerplexity

Perplexity's high-quality general-purpose model with real-time web search and citations.

Sonar Reasoning ProPerplexity

Perplexity's advanced reasoning model with strong analytical depth and live web context.

Sonar Deep ResearchPerplexity

Perplexity's deepest research-focused model with comprehensive web-grounded responses and citations.

Kimi K2.5Moonshot AI

Moonshot AI's latest model with image understanding, tool usage, and strong coding capabilities.

Kimi K2Moonshot AI

Moonshot AI's instruction-tuned model with tool usage and strong coding capabilities.

Grok Code Fast 1xAI

xAI's fast coding model.

Grok 4.1 FastxAI

xAI's fastest model. Non-reasoning model.

Grok 4.1 Fast (Reasoning)xAI

xAI's fastest model. Reasoning model.

Grok 4xAI

xAI's latest model.

Grok 4 FastxAI

xAI's fastest model. Non-reasoning model.

Grok 4 Fast (Reasoning)xAI

xAI's fastest model. Reasoning model.

Claude Opus 4.6Anthropic

The latest model from Anthropic, upgraded version of opus 4.5 Exceptional model for specialized reasoning tasks. Very powerful, reasonable price.

Claude Opus 4.5Anthropic

The latest model from Anthropic. Exceptional model for specialized reasoning tasks. Very powerful, reasonable cost.

Claude Sonnet 3.7Anthropic

The last generation model from Anthropic. Better at code, math, and more. But slow and expensive.

Claude Sonnet 4Anthropic

The previous generation model from Anthropic. Claude Sonnet 4 is a significant upgrade to Claude Sonnet 3.7, delivering superior coding and reasoning while responding more precisely to your instructions.

Claude Opus 4.1Anthropic

Exceptional model for specialized reasoning tasks from Anthropic. Very powerful, but very expensive.

Claude Sonnet 4.5Anthropic

The latest model from Anthropic. Claude Sonnet 4.5 is Anthropic's most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.Sonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.

Claude Haiku 4.5Anthropic

Claude Haiku 4.5 is Anthropic's fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4's performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications. It introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world's best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.

GPT-5.2 CodexOpenAI

OpenAI's most intelligent coding model optimized for long-horizon, agentic coding tasks.

GPT-5 ProOpenAI

GPT-5 pro uses more compute to think harder and provide consistently better answers.

GPT-5.2 ProOpenAI

Version of GPT-5.2 that produces smarter and more precise responses.

GPT-5.2OpenAI

OpenAI's flagship model for coding and agentic tasks across industries.

GPT-4o MiniOpenAI

Like gpt-4o, but faster. This model sacrifices some of the original GPT-4o's precision for significantly reduced latency. It accepts both text and image inputs.

GPT-4.1 NanoOpenAI

For tasks that demand low latency, GPT‑4.1 nano is the fastest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It's ideal for tasks like classification or autocompletion.

GPT-4oOpenAI

OpenAI's flagship non-reasoning model. Works with text and images. Relatively smart. Good at most things.

GPT-4.1 NanoOpenAI

For tasks that demand low latency, GPT‑4.1 nano is the fastest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It's ideal for tasks like classification or autocompletion.

GPT-4.1 MiniOpenAI

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency. It has a very large context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider's polyglot diff benchmark) and vision understanding.

GPT-4.1OpenAI

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks.

GPT-OSS 20bOpenAI

A medium-sized open-weight model from OpenAI suitable for general-purpose tasks.

GPT-OSS 120bOpenAI

OpenAI's largest open-weight model

GPT-5 NanoOpenAI

An ultra-fast GPT-5 variant tuned for low-latency tasks with reasoning and tool use.

GPT-5 MiniOpenAI

A lighter-weight GPT-5 variant optimized for speed while retaining strong reasoning and tool use.

GPT-5OpenAI

ullamco adipisicing velit laboris

GPT-5.1OpenAI

OpenAI's latest flagship model. PhD-level intelligence at most things.

DeepSeek ReasonerDeepSeek

DeepSeek's reasoning model.

DeepSeek ChatDeepSeek

DeepSeek's latest model.