Claude Sonnet 5.5 vs GPT-5.4 Mini: cost per task
GPT-5.4 Mini is cheaper on 14 of 14 tasks and about 3.9x cheaper on average (geometric mean). Claude Sonnet 5.5 has the higher LMArena Text score (1475 vs 1447).
| Task | Claude Sonnet 5.5 | GPT-5.4 Mini | Difference |
|---|---|---|---|
| Answer a chat question | 1.3¢ | 0.53¢ | 2.4x |
| Reply to a customer email | 0.40¢ | 0.06¢ | 6.4x |
| Write a 1,500-word blog post | 3.7¢ | 1.1¢ | 3.4x |
| Write 10 product descriptions | 4.4¢ | 0.48¢ | 9.2x |
| Translate 1,000 words | 2.6¢ | 0.73¢ | 3.5x |
| Proofread one page (500 words) | 1.1¢ | 0.39¢ | 2.8x |
| Summarize a 20-page PDF | 4.5¢ | 1.2¢ | 3.7x |
| Extract data from an invoice | 1.0¢ | 0.28¢ | 3.7x |
| Analyze a 200-row spreadsheet | 17¢ | 1.6¢ | 10.6x |
| Answer from 5 retrieved documents (RAG) | 2.7¢ | 0.43¢ | 6.4x |
| Classify 100 support tickets | 0.89¢ | 0.56¢ | 1.6x |
| Review 500 lines of code | 8.0¢ | 2.7¢ | 2.9x |
| Write a SQL query | 1.1¢ | 0.36¢ | 3.0x |
| Run a 50-step coding agent | 84¢ | 32¢ | 2.6x |
Specs and list prices
| Claude Sonnet 5.5 | GPT-5.4 Mini | |
|---|---|---|
| Input per 1M | $2.00 | $0.75 |
| Output per 1M | $10.00 | $4.50 |
| Cached input per 1M | $0.10 | $0.075 |
| Context | 1M | 400K |
| Providers | 8 | 5 |
| Reasoning | always | default |
| LMArena Text | 1475 | 1447 |
| Released | Sep 28, 2026 | Mar 17, 2026 |
FAQ
Is Claude Sonnet 5.5 or GPT-5.4 Mini cheaper?
GPT-5.4 Mini is cheaper on 14 of 14 tasks and about 3.9x cheaper on average (geometric mean). Claude Sonnet 5.5 has the higher LMArena Text score (1475 vs 1447).
How much does Claude Sonnet 5.5 cost compared to GPT-5.4 Mini per token?
Claude Sonnet 5.5: $2.00 input and $10.00 output per 1M tokens. GPT-5.4 Mini: $0.75 input and $4.50 output. Token prices alone mislead - models use different numbers of tokens for the same task, which is what the task table shows.