For Developers/Models/Compare

Model comparisons

Compare AI Models

Side-by-side breakdowns: pricing, context window, benchmarks, and what each model actually wins at.

Build your own comparison

Pick any two models - comparison renders instantly

Editorial comparisons

Claude Sonnet 5vsGPT-5.6

1M ctx|$3.00 inputvs5 input

Claude Opus 4.8vsGemini 3.5

1M ctx|$5.00 inputvs$1.50 input

Claude Sonnet 5vsGemini 3.5

1M ctx|$3.00 inputvs$1.50 input

Claude Opus 4.8vsGPT-5.6 Sol

1M ctx|$5.00 inputvs$5.00 input

Claude Opus 4.8vsClaude Sonnet 5

1M ctx|$5.00 inputvs$3.00 input

Claude Sonnet 5vsGPT-5.5

1M ctx|$3.00 inputvs$5.00 input

DeepSeek V4vsLlama 4

1M tokens ctx|Free inputvsFree input

Claude Sonnet 5vsDeepSeek V4

1M ctx|$3.00 inputvsFree input

Gemini 3.5vsGPT-5.6

1,048,576 tokens (Gemini 3.5 Flash; Pro variant not yet released) ctx|$1.50 inputvs5 input

Claude Haiku 4.5vsGemini 2.5 Flash

200K ctx|$1.00 inputvs$0.30 input

DeepSeek V4vsQwen 3

1M tokens ctx|Free inputvsFree input

400,000 tokens (128,000 max output) ctx|$1.25 inputvs$5.00 input

GPT-4ovsMistral Large

128,000 tokens (16,384 max output) ctx|$2.50 inputvs2.00 input

Llama 4vsQwen 3

Up to 10M tokens (Scout); ~1M tokens (Maverick) ctx|Free inputvsFree input

Claude Fable 5vsGPT-5.6 Sol

1M ctx|$10.00 inputvs$5.00 input

← All AI models