All models. One place.
Explore model capabilities and find the right fit for your next project.
Text
- Google DeepMind · Text
Gemini 4 Argon
Google's reasoning model for complex software engineering and long-horizon professional tasks.
Input 400 / Output 2,000credits / 1M tokens - OpenAI · Text
GPT-6 Astra
OpenAI's Astra model for demanding reasoning, coding, research and professional work.
Input 1,000 / Output 5,000credits / 1M tokens - OpenAI · Text
GPT-6 Sol
The GPT-6 Sol API model for balanced reasoning and everyday development workflows.
Input 200 / Output 1,000credits / 1M tokens - OpenAI · Text
GPT-6 Luna
OpenAI's efficient GPT-6 model for focused tasks and high-volume workloads.
Input 10 / Output 50credits / 1M tokens - OpenAI · Text
GPT-6.1 Sol
GPT-6.1 Sol balances complex-work intelligence, speed and cost.
Input 200 / Output 1,000credits / 1M tokens - OpenAI · Text
GPT-5.6
The GPT-5.6 alias for GPT-5.6 Sol, with adjustable reasoning and a large context window.
Input 500 / Output 3,000credits / 1M tokens - Anthropic · Text
Claude Opus 5.5
Anthropic's Opus model for long-running agentic coding and complex knowledge work.
Input 400 / Output 2,000credits / 1M tokens - Anthropic · Text
Claude Haiku 5.5
Claude's compact model for high-volume classification, extraction and responsive agent tasks.
Input 10 / Output 50credits / 1M tokens - Anthropic · Text
Claude Opus 5
Claude Opus 5 for complex agentic coding, extended reasoning and enterprise work.
Input 500 / Output 2,500credits / 1M tokens - Anthropic · Text
Claude Sonnet 5.5
Claude's balanced model for everyday engineering, bug fixes and polished professional artifacts.
Input 200 / Output 1,000credits / 1M tokens - Google DeepMind · Text
Gemini 3.8 Flash
Google's Flash workhorse for software engineering, agents and multimodal enterprise tasks.
Input 150 / Output 750credits / 1M tokens - Google DeepMind · Text
Gemini 3.1 Pro
Gemini Pro preview for grounded multimodal reasoning and precise multi-step tool workflows.
Input 200 / Output 1,200credits / 1M tokens - xAI · Text
Grok 4.7
Grok's frontier model for coding, sustained agent tasks and professional knowledge work.
Input 200 / Output 600credits / 1M tokens - Moonshot AI · Text
Kimi K3
Moonshot's Kimi model for long-horizon coding and end-to-end knowledge work with vision.
Input 300 / Output 1,500credits / 1M tokens - DeepSeek · Text
DeepSeek V4.1 Flash
DeepSeek's multimodal Flash model with an asymmetric mixture-of-experts architecture.
Reference priceInput 30 / Output 120Cached input 0.6credits / 1M tokens - OpenAI · Text
GPT-6.1 Terra
GPT-6.1 Terra text conversations on OneAster.
Input 100 / Output 500credits / 1M tokens
No more models