Compare LLM API pricing side by side

Pick 2-4 models and compare prices, quality, and cost per request side by side. The URL updates as you go: copy it to share this exact comparison. Data snapshot: 2026-10-04.

Each comparison lines up input and output token prices, batch and prompt-cache rates where the provider publishes them, Arena ELO, and cost per request across the 8 business use-case profiles, at list price and after discounts.

Head-to-head comparisons

20 ready-made pairs. Open one to see the two models side by side, then add up to 2 more.

• Claude Sonnet 5 vs GPT-5.5
• Claude Opus 5 vs GPT-5.5
• Claude Opus 5 vs Gemini 3.1 Pro Preview
• Claude Fable 5 vs GPT-5.5 Pro
• Claude Sonnet 5 vs Gemini 3.7 Flash
• DeepSeek V4 Flash 0731 vs Gemini 3.7 Flash
• DeepSeek V4 Pro 0813 vs Qwen3.7 Max
• GPT-5.5 vs Gemini 3.1 Pro Preview
• Claude Sonnet 5 vs DeepSeek V4 Pro 0813
• Kimi K3 vs Claude Opus 5
• GLM 5.2 vs DeepSeek V4 Flash 0731
• Grok 4.6 vs GPT-5.5
• Claude Haiku 4.5 vs GPT-5.6 Luna
• MiniMax M3 vs GLM 5.2
• Llama 4 Maverick vs DeepSeek V3.2
• Qwen3.7 Plus vs Gemini 3.7 Flash
• Claude Opus 5 vs Claude Sonnet 5
• GPT-5.5 vs GPT-5.4
• Gemini 3.1 Pro Preview vs Gemini 3.5 Flash
• Claude Fable 5 vs Claude Opus 5

Build your own

The interactive tool takes any 2 to 4 models from the catalogue and writes the selection into the URL, so a comparison can be shared or exported as CSV. Start from the full model list and pick from there.

LLM pricing · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server