Claude Haiku 5.5 vs Mistral Large 4: cost per task
Claude Haiku 5.5 is cheaper on 14 of 14 tasks and about 7.7x cheaper on average (geometric mean).
| Task | Claude Haiku 5.5 | Mistral Large 4 | Difference |
|---|---|---|---|
| Answer a chat question | 0.07¢ | 0.29¢ | 4.4x |
| Reply to a customer email | 0.04¢ | 0.76¢ | 21.4x |
| Write a 1,500-word blog post | 0.19¢ | 1.6¢ | 8.6x |
| Write 10 product descriptions | 0.21¢ | 0.66¢ | 3.1x |
| Translate 1,000 words | 0.13¢ | 2.6¢ | 20.9x |
| Proofread one page (500 words) | 0.07¢ | 0.92¢ | 12.9x |
| Summarize a 20-page PDF | 0.22¢ | 1.4¢ | 6.2x |
| Extract data from an invoice | 0.06¢ | 0.58¢ | 9.1x |
| Analyze a 200-row spreadsheet | 0.85¢ | 2.6¢ | 3.0x |
| Answer from 5 retrieved documents (RAG) | 0.14¢ | 0.92¢ | 6.4x |
| Classify 100 support tickets | 0.09¢ | 1.6¢ | 17.7x |
| Review 500 lines of code | 0.66¢ | 2.2¢ | 3.4x |
| Write a SQL query | 0.08¢ | 0.67¢ | 7.9x |
| Run a 50-step coding agent | 6.6¢ | 52¢ | 7.9x |
Specs and list prices
| Claude Haiku 5.5 | Mistral Large 4 | |
|---|---|---|
| Input per 1M | $0.10 | $0.68 |
| Output per 1M | $0.50 | $2.09 |
| Cached input per 1M | $0.01 | $0.07 |
| Context | 1M | 1M |
| Providers | 10 | 3 |
| Reasoning | default | default |
| LMArena Text | - | 1432 |
| Released | Oct 7, 2026 | Oct 6, 2026 |
FAQ
Is Claude Haiku 5.5 or Mistral Large 4 cheaper?
Claude Haiku 5.5 is cheaper on 14 of 14 tasks and about 7.7x cheaper on average (geometric mean).
How much does Claude Haiku 5.5 cost compared to Mistral Large 4 per token?
Claude Haiku 5.5: $0.10 input and $0.50 output per 1M tokens. Mistral Large 4: $0.68 input and $2.09 output. Token prices alone mislead - models use different numbers of tokens for the same task, which is what the task table shows.