GPT-6 Luna vs Claude Haiku 5.5 vs DeepSeek V4 Flash 0423
Short answer
GPT-6 Luna ($0.10 in / $0.50 out); Claude Haiku 5.5 ($0.10 in / $0.50 out); DeepSeek V4 Flash 0423 ($0.09 in / $0.18 out). Lowest listed input price: DeepSeek V4 Flash 0423. Longest listed context: GPT-6 Luna at 1,050,000 tokens. A lower price is not a quality ranking.
Side-by-side facts. The third-party index is copied when the feed has one. Unknown means it did not.
OpenRouter describes GPT-6 Luna as the fast, cost-efficient GPT-6 model for high-volume work such as chat, classification, and light agent steps. It is the reviewed cheap OpenAI option.
GPT-6 Luna is listed at $0.10 input and $0.50 output per million tokens, with a 1,050,000-token context window.
OpenRouter describes Claude Haiku 5.5 as Anthropic's small, fast model for high-volume work such as summarisation, subagents, and browser use. Stronger than Haiku 4.5 at coding, on the listing's own words, and far cheaper than Sonnet.
Claude Haiku 5.5 is listed at $0.10 input and $0.50 output per million tokens, with a 1,000,000-token context window.
The April 2026 V4 Flash row is the cheapest reviewed text model with a million-token window and open weights. It does not accept images. Use it for bulk text.
DeepSeek V4 Flash 0423 is listed at $0.09 input and $0.18 output per million tokens, with a 1,048,576-token context window.