Claude Haiku 4.5 vs Codestral 25.01

Codestral 25.01 is cheaper than Claude Haiku 4.5 by about 78% on a blended (75% input / 25% output) basis. Claude Haiku 4.5 charges $1.00 / $5.00 per 1M input/output tokens; Codestral 25.01 charges $0.30 / $0.90.

FieldClaude Haiku 4.5Codestral 25.01
Input $/Mtok$1.00$0.30
Output $/Mtok$5.00$0.90
Cache read $/Mtok$0.10$0.0300
Cache write $/Mtok$1.25–
Input $/Mcharn/a0.11
Output $/Mcharn/a0.32
Context window200000262144
Tokenizerclaudemistral
Confidence?officialaggregator
Sourceofficial-anthropicmodelsdev

Confidence: official = vendor pricing page · api = OpenRouter per-host · aggregator = community list, may lag · unreviewed = automatic extraction awaiting review. When sources disagree the most authoritative wins. Details: /methodology#confidence

Price history

No price changes recorded yet for either model.

Same workload, monthly cost

Illustrative monthly cost at 10M tokens/month, split per workload preset. Not a substitute for the calculator, which uses your own volume, cache and batch assumptions.

WorkloadClaude Haiku 4.5Codestral 25.01
Coding agent$12.00$3.30
RAG chat$16.00$3.90
Summarisation (batch)$14.00$3.60
Classification$10.80$3.12
Chat assistant$26.00$5.40
Content generation$42.00$7.80

Batch pricing not published for Claude Haiku 4.5; standard rate used for the batch share of a workload.

Batch pricing not published for Codestral 25.01; standard rate used for the batch share of a workload.

Cite this page

Claude Haiku 4.5 vs Codestral 25.01: $1.00/$5.00 vs $0.30/$0.90 per 1M tokens as of 2026-11-19. Token Barometer by Dejan Strbad, https://tokenbarometer.com, data CC BY 4.0. https://tokenbarometer.com/compare/anthropic_claude-haiku-4-5-vs-mistral_codestral-2501

Claude Haiku 4.5 page | Codestral 25.01 page | Open Claude Haiku 4.5 in calculator | Open Codestral 25.01 in calculator