Claude Haiku 5.5 vs Codestral 25.08
Price and specs side by side · USD per 1M tokens · verified 2026-10-11
// side by side
| metric | Claude Haiku 5.5 | Codestral 25.08 |
|---|
| input / 1M | $0.10 | $0.30 |
| output / 1M | $0.50 | $0.90 |
| blended (3:1) | $0.20 | $0.45 |
| cache read / 1M | $0.01 | $0.03 |
| context | 1M | 256K |
| max output | 128K | 8.2K |
| input types | text · image · pdf | text |
| reasoning | yes | no |
| tool calling | yes | yes |
| structured output | yes | yes |
| open weights | no | no |
| released | 2026-10-07 | 2025-07-30 |
| knowledge cutoff | 2026-06 | n/a |
| lab | Anthropic | Mistral |
// monthly cost scenarios
| workload | tokens in / out | Claude Haiku 5.5 | Codestral 25.08 |
|---|
| Chatbot | 10M / 2M | $2.00 | $4.80 |
| RAG app | 50M / 5M | $7.50 | $19.50 |
| Coding agent | 20M / 10M | $7.00 | $15.00 |
// verdict
- Claude Haiku 5.5 is 55.6% cheaper than Codestral 25.08 on a blended 3:1 input/output basis.
- Claude Haiku 5.5 has the larger context window (1M vs 256K tokens).
- Only Claude Haiku 5.5 supports built-in reasoning.
- Only Claude Haiku 5.5 accepts image input.