← lab

Model Comparison

Filter, sort, and compare AI models side by side.

Model ↑ProviderContextInput /1MOutput /1MStrengths
Claude Haiku 4.5Anthropic200K$1$5Speed, cost efficiency, high volume
Claude Opus 4.6Anthropic200K$15$75Most capable Claude, complex reasoning, agentic tasks
Claude Sonnet 4.5Anthropic1M$3$15Near-Opus intelligence at Sonnet pricing
DeepSeek R1OSSDeepSeek64K$0.56$1.68Open-source reasoning, competes with o1
DeepSeek V3OSSDeepSeek163K$0.56$1.68Cheap, strong general-purpose, open weights
Gemini 2.0 FlashGoogle1.048M$0.1$0.4Rock-bottom pricing, speed, multimodal
Gemini 2.5 FlashGoogle1.048M$0.3$2.5Cheap thinking model, massive context
Gemini 2.5 ProGoogle1.048M$1.25$10Thinking model, coding, huge context
GPT-4.1OpenAI1.047M$2$8Million-token context, coding, instruction following
GPT-4oOpenAI128K$2.5$10Multimodal, general purpose
GPT-5OpenAI400K$1.25$10Massive context, strong all-rounder
GPT-5 MiniOpenAI400K$0.25$2Budget GPT-5 class, large context
GPT-5 NanoOpenAI400K$0.05$0.4Cheapest frontier model, on-device capable
Kimi k2Moonshot AI131K$0.5$2.4Long-context reasoning, competitive pricing
Llama 4 MaverickOSSMeta1.048MFree*Free*Strong open-source, 1M context, multimodal
Llama 4 ScoutOSSMeta327KFree*Free*10M context, MoE architecture, self-hostable
Mistral Large 3Mistral262K$0.5$1.5Multilingual, code, reasoning, larger context
Mistral Small 3.1Mistral128K$0.35$0.56Very cheap, strong for its size
o3OpenAI200K$2$8Reasoning, maths, science, coding
o3-miniOpenAI200K$1.1$4.4Budget reasoning model, structured thinking
Qwen 2.5 72BOSSAlibaba32KFree*Free*Strong multilingual, coding, open weights

21 of 21 models shown. Prices per 1M tokens (USD). *Open source models are free to self-host.