Claude Haiku 5.5 vs GPT-6.1 Sol

Where it leads

• Lower input and output prices, $0.10 and $0.50 vs $2 and $10 per 1M tokens
• Cheaper cached input, $0.01 vs $0.10 per 1M tokens
• Batch pricing, $0.05 input and $0.25 output per 1M tokens

Best for

• High-volume classification, extraction and routing under the 100,000-token line
• Cost-sensitive fan-out steps where a frontier model is overkill

Watch out for

• Priced by prompt length, and it is a cliff rather than a taper: a request whose prompt passes 100,000 tokens is billed at $0.50 input and $2.50 output for the whole request, five times the short rate
• Cache reads and cache writes both count toward that 100,000-token measurement, so a large cached prefix can tip a request into the higher band on its own
• It is the only current Claude model whose 1M window is not priced uniformly; every other 4.6-and-later model bills a 900k request at the same rate as a 9k one

Where it leads

• Higher Arena Text score, 1481 Elo vs 1425 Elo
• Higher Arena WebDev score, 1751 Elo vs 1589 Elo
• Higher FrontierMath Tiers 1-3 (v2) score, 93.7% vs 75.1%
• Higher GPQA Diamond score, 95.4% vs 89.6%
• Higher SimpleQA Verified score, 73.9% vs 23.8%
• Larger context window 1,050,000 vs 1,000,000 tokens

Best for

• Agent loops that replay a large cached prefix
• A drop-in alternative to GPT-6 Sol at the same base cost

Watch out for

• The same 272,000-token long-context cliff applies, rebilling the full request at $4 input and $15 output
• Released a week after GPT-6 Sol at identical base pricing, so the two are easy to confuse on a rate card; the cached rate is the difference