Best LLMs
Large language models for general-purpose text generation, reasoning, summarization, and conversation. Capable of understanding complex instructions and producing high-quality, coherent text responses.
Models
Gemini 4 Argon
compatible APIGoogle's frontier Gemini model for long-horizon coding, enterprise knowledge work, and cyber defense
Claude Opus 5.5
compatible APITop-capability Claude model for long-horizon agents, complex coding, and deep reasoning
Claude Fable 5.1
compatible APIFrontier multimodal model for long-running coding, research, and professional work
Claude Opus 5
compatible APIHigh-capability Claude model for deep reasoning, long-horizon agents, and complex coding and enterprise work
Gemini 3.8 Flash
compatible APIGoogle's most capable Flash model for long-horizon coding, autonomous agents, and complex multimodal work
Kimi K3
compatible APIFlagship multimodal reasoning LLM for long-horizon coding, knowledge work, and tool-rich agent workflows
Claude Sonnet 5.5
compatible APIFast, cost-efficient Claude model for everyday coding, agents, and knowledge work
GLM-5.3
compatible APIFlagship coding and agentic LLM with stronger long-horizon execution and security-oriented reasoning
DeepSeek-V4.1-Flash-1017
compatible APIMultimodal 1M-context MoE checkpoint for coding, reasoning, and tool-using agents
GPT-6.1 Sol
compatible APIUpgraded reasoning model for coding, computer use, and professional work
GPT-6 Astra
compatible APIFrontier reasoning and tool-use model for demanding end-to-end professional workflows
Frontier reasoning LLM for complex coding, long-context work, and tool-using professional tasks
DeepSeek-V4-Pro-0813
compatible APIHigh-capability frontier LLM with 1M context, stronger agent performance, and dual thinking modes
GPT-6 Luna
compatible APIEfficient reasoning model for focused, high-volume text and vision workloads
Claude Haiku 5.5
compatible APIFastest, lowest-cost Claude model for high-volume agents, extraction, and low-latency applications
Open-weight alternatives
GLM-5.3-Flash
Efficient multimodal GLM for coding, agents, and long-context visual understanding
$0.15 / 1M tokens · Input tokensGemma 4 31B
Open 31B multimodal reasoning model for coding, long context, and agentic workflows
$0.102 / 1M tokens · Input tokensDeepSeek-V4.1-Flash
Multimodal 1M-context MoE for efficient coding, reasoning, and long-horizon agent workflows
$0.15 / 1M tokens · Input tokensShieldstral 1.0 3B
Compact multimodal moderation model that judges text and images against your own policy
$0.09 / 1M tokens · Input tokens