Models and providers

Claude Fable 5 is a Mythos-class model for autonomous knowledge work and coding. It handles text, image, and file inputs to produce text outputs with reasoning support.

Claude Opus 5 is a flagship model excelling at demanding reasoning, coding, and long-horizon agentic tasks, including software development and visual analysis.

Sonnet 5 is Anthropic's most capable Sonnet model, excelling in coding, agents, and professional tasks with selectable reasoning effort levels.

Fastest, most affordable Claude for everyday tasks.

Balanced Claude with strong quality at a moderate price.

Newest Opus — top-tier coding, analysis, and long-horizon tasks.

Most capable Claude for deep reasoning and agentic work.

Claude Sonnet 4.5 is an advanced model optimized for agentic workflows and coding. It excels at complex coding tasks and benchmarks.

This model excels at complex reasoning, coding, and agentic workflows, particularly with command-line and multi-step coding tasks.

A balanced model for everyday coding, reasoning, and agentic tasks.

A fast, cost-efficient model for high-volume, latency-sensitive tasks like chat and classification. It offers capable reasoning for lightweight agentic workflows.

Latest frontier model with the strongest general capabilities.

GPT-5.4 Pro is OpenAI's most advanced model, excelling at complex, high-stakes reasoning tasks with its enhanced capabilities.

Higher-quality reasoning for complex, multi-step tasks.

Fast and cheap for high-volume, latency-sensitive workloads.

A fast, cost-efficient model for high-volume tasks, supporting text and image inputs with low latency.

This model combines advanced reasoning with image generation for multimodal workflows. It excels at tasks involving text, code, and visual content.

Balanced flagship for everyday reasoning, chat, and tool use.

GPT-5 Mini is a smaller, faster, and cheaper version of GPT-5, ideal for lighter reasoning tasks while retaining instruction-following and safety features.

This advanced LLM excels at complex instruction following, software engineering tasks, and reasoning over very long contexts.

A mid-sized model offering GPT-4o-level performance with lower latency and cost. It excels with a large context window and strong performance on challenging tasks.

This is OpenAI's latest multimodal model, accepting text and image inputs to generate text outputs. It offers GPT-4 Turbo intelligence with enhanced speed.

This advanced small model handles text and image inputs, generating text outputs. It offers powerful capabilities at a significantly reduced cost.

Gemini 3.6 Flash is a fast, efficient model for coding and agentic workflows, producing polished outputs with minimal edits.

Latest Flash generation, optimised for speed and scale.

Refined Gemini 3 Pro with an even larger 2M-token context.

Gemini 3.1 Flash Lite is a high-efficiency multimodal model for low-latency, high-volume tasks. It handles text, image, video, audio, and PDF inputs.

A high-efficiency model for high-volume use cases, offering improved quality and performance.

A fast, cost-effective model for agentic workflows, chat, and coding, offering near Pro-level reasoning.

High-quality reasoning across text, images, and code.

Fast, low-cost multimodal model with a huge context window.

A fast, cost-efficient reasoning model for low-latency applications. It excels at quick text generation and high throughput.

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model excelling at advanced reasoning and coding tasks.

An efficiency-optimized Mixture-of-Experts model designed for fast inference. It excels at handling long contexts and complex reasoning tasks.

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.

Kimi K3 is an open-weight multimodal reasoning model adept at complex coding, knowledge work, and long-horizon agentic workflows.

Kimi K2.7 Code is a coding-focused model designed for reliable, end-to-end programming tasks over long contexts. It utilizes a multimodal mixture-of-experts architecture.

Kimi K2.6 is a multimodal model excelling at long-horizon coding, UI/UX generation, and multi-agent orchestration across Python, Rust, and Go.

Kimi K2.5 is a multimodal model excelling at visual coding and agent swarm coordination. It leverages extensive pretraining for advanced capabilities.

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering, and complex multi-step automation.

GLM-5.1 excels at long-horizon coding tasks, offering independent and continuous operation for complex development.

This multimodal foundation model accepts text, image, and video inputs to generate text outputs, excelling at long-horizon agentic tasks and coding.

MiniMax-M2.7 is a large language model designed for autonomous productivity and continuous improvement. It excels at active participation in its own evolution through advanced agentic capabilities.

Grok 4.5 is SpaceXAI's most advanced model, excelling in coding, knowledge work, and STEM tasks.

Qwen3.7-Max is a flagship model for agent-centric workloads, excelling at coding and office productivity tasks.

A multimodal model that excels at text generation and understanding, with enhanced capabilities for image processing.

Qwen3.6 Flash is a fast, efficient multimodal model supporting text, image, and video input. It excels at processing long contexts.

Qwen3.5 Flash models are efficient vision-language models with a hybrid architecture, excelling at fast inference for multimodal tasks.

Qwen 3.6 Plus is a powerful, scalable LLM with a hybrid architecture, excelling at high-performance inference.

Qwen3-Max is an advanced LLM with enhanced reasoning, instruction following, and multilingual capabilities. It excels at understanding and generating text across diverse topics and languages.