Defaults follow the 3:1 blend: 3,000,000 input tokens and 1,000,000 output tokens. Move either slider, or type a volume.
Claude Haiku 5.5$0.80
GPT-6 Luna$0.80
DifferenceSame monthly cost
Questions
Which is cheaper on a 3:1 blend, Claude Haiku 5.5 or GPT-6 Luna?
Claude Haiku 5.5 and GPT-6 Luna land on the same 3:1 blended price, $0.20 per 1M tokens. The blend is (3 × input + 1 × output) / 4.
How do the Claude Haiku 5.5 and GPT-6 Luna context windows compare?
GPT-6 Luna has the longer context window at 1,050,000 tokens, compared with Claude Haiku 5.5 at 1,000,000 tokens, a difference of 50,000 tokens.
What does a month of 3,000,000 input tokens and 1,000,000 output tokens cost?
At 3,000,000 input tokens and 1,000,000 output tokens, Claude Haiku 5.5 costs $0.80 and GPT-6 Luna costs $0.80. The monthly cost is the same for both models. This volume uses the same 3:1 ratio as the blended price.