Claude Haiku 5.5 Consumes 3X More Tokens Than ChatGPT 6 Luna

Anthropic released Claude Haiku 5.5, a faster and cheaper model for high-volume tasks. It is 75% cheaper than Haiku 4.5 for prompts under 100,000 tokens, but in token-intensive workloads it consumes up to three times more tokens than GPT6 Luna, offsetting the savings.

• Haiku 5.5 is 75% cheaper than Haiku 4.5 for tasks under 100,000 tokens
• Token consumption is up to 3x higher than GPT6 Luna
• Best suited as a sub-agent in multi-model setups
• Falls short of Sonnet 5.5 and GPT6.1 Soul in advanced reasoning