Model catalog
Every model available in AiFuse, with the price you pay. No subscriptions.
Anthropic$$$$Claude Fable 5.1
Anthropic's latest Fable release for the hardest reasoning and long-horizon agentic work.
Anthropic$$$Claude Opus 5.5
Anthropic's Opus 5.5 — adaptive thinking always on, with effort controlling how deeply it reasons.
Anthropic$$Claude Sonnet 5.5
Anthropic's Sonnet 5.5 — fast, capable everyday model, strong at coding.
Anthropic$$$$Claude Fable 5
Anthropic's most advanced model for the hardest reasoning and long-horizon agentic work.
Anthropic$$Claude Sonnet 5
Balanced, versatile workhorse for daily use and scaled production.
Anthropic$$$Claude Opus 5
Anthropic's latest flagship for deep reasoning and long-horizon agentic coding. 1M context.
Anthropic$$$Claude Opus 4.8
Highly autonomous flagship for complex reasoning, long-horizon agentic coding, and knowledge work.
Anthropic$Claude Haiku 4.5
Fastest and most affordable for quick answers
DeepSeek$$DeepSeek V4 Pro
Flagship 1.6T-parameter MoE reasoning for complex coding, multi-step analysis, and long-horizon agentic work, at frontier quality.
DeepSeek$DeepSeek V4.1 Flash
DeepSeek's fast V4.1 release — low-cost general chat with aggressive prompt caching.
DeepSeek$DeepSeek V4 Flash
Fast and affordable with strong coding and analysis. 128K context.
Google$$Gemini 3.1 Pro
Google's flagship reasoning model with strong multimodal and long-context performance.
Google$$Gemini 3.8 Flash
Google's headline Flash model. Fast, high quality, 1M context.
Google$Gemini 3.5 Flash-Lite
Google's cheapest Flash tier. Fast and low cost, 1M context.
Z.ai$$GLM 5.3
Z.ai's open model for long-context coding and agentic work, with a 1M-token context window.
xAI$$$Grok 4.7
xAI's latest Grok release for reasoning, coding and analysis.
xAI$$Grok Build
Fast coding model for agentic workflows. 256K context.
xAI$$$Grok 4.6
Frontier reasoning model. 500K context.
xAI$$Grok 4.5
Frontier reasoning model. 200K context.
xAI$$Grok 4.3
xAI's most powerful model with extended reasoning capability.
Mistral AI$$Mistral Medium 3.5
Mistral's newest frontier model for agentic work and coding, with image input — newer and stronger than Large 3.
Mistral AI$Mistral Large 3
Mistral's open-weight general model, multilingual with image input — older and cheaper than Medium 3.5, despite the name.
Mistral AI$Codestral
Mistral's code specialist — fast, low-cost code generation.
Mistral AI$Mistral Small 4
Mistral's lightweight model — fast and very low cost, with image input.
Moonshot$$Kimi K3
Moonshot's reasoning model with a 1M-token context and native vision. Strong multi-step problem solving.
Moonshot$$Kimi K2.7 Code
Moonshot's coding-specialist Kimi with a 1M-token context. Tuned for code generation, editing, and repo-scale reasoning.
OpenAI$$$$GPT-6 Astra
OpenAI's GPT-6 flagship for the most complex reasoning and agentic work.
OpenAI$$$GPT-6.1 Sol
OpenAI's GPT-6.1 model for complex reasoning and agentic work.
OpenAI$GPT-6 Luna
OpenAI's fast, low-cost GPT-6 model for high-volume tasks.
OpenAI$$$GPT-5.6 Sol
OpenAI's top-tier GPT-5.6 model for the most complex reasoning and agentic tasks.
OpenAI$$$$GPT-5.5 Pro
OpenAI's specialist GPT-5.5 Pro model for the hardest, highest-stakes reasoning.
OpenAI$$GPT-5.6 Terra
OpenAI's balanced GPT-5.6 model for everyday complex tasks and reasoning.
OpenAI$$GPT-5.6 Luna
OpenAI's fast, cost-efficient GPT-5.6 model for high-volume tasks.
OpenAI$$$GPT-5.5
Flagship reasoning model. 1.05M context, 128K output. Highest-end OpenAI tier.
OpenAI$$GPT-5.4
OpenAI's flagship model for complex tasks and advanced reasoning.
OpenAI$GPT-5.4 Nano
Ultra-fast and ultra-cheap for simple and repetitive tasks.
Perplexity$$Perplexity Sonar Pro
Advanced web-grounded search with deeper reasoning and more citations. 200K context.
Perplexity$$Perplexity Sonar Reasoning Pro
Web-grounded reasoning with chain-of-thought and real-time citations. 128K context.
Perplexity$Perplexity Sonar
Web-grounded AI search with real-time citations. 127K context.