Comparison

Claude Haiku 4.5 vs Mistral Small 4

Claude Haiku 4.5 charges 85% more per input token than Mistral Small 4. Mistral Small 4 is 88% cheaper on output tokens. Claude Haiku 4.5 offers a cheaper cached-input tier for repeated context.

FieldClaude Haiku 4.5
Mistral Small 4
ProviderAnthropicMistral AI
Context window200K
Max output64K
Input / 1M$1.00$0.1585% cheaper
Output / 1M$5.00$0.6088% cheaper
Cached input / 1M$0.10
Batch discount50%50%
Release date2025-10-01

Worked cost examples

Estimated monthly cost on three common usage shapes

WorkloadClaude Haiku 4.5Mistral Small 4

Chatbot

800 input / 200 output tokens per request, 100,000 requests/month

$180.00$24.00cheaper

RAG pipeline

6,000 input / 700 output tokens per request, 30,000 requests/month

$285.00$39.60cheaper

Batch summarization

20,000 input / 1,500 output tokens per request, 5,000 requests/month

$137.50$19.50cheaper

Claude Haiku 4.5 vs Mistral Small 4 FAQ

Is Claude Haiku 4.5 cheaper than Mistral Small 4?
Claude Haiku 4.5 costs $1.00 per 1M input tokens versus $0.15 for Mistral Small 4 — Mistral Small 4 is 567% cheaper per input token.
Which is cheaper for output tokens, Claude Haiku 4.5 or Mistral Small 4?
Claude Haiku 4.5 charges $5.00 per 1M output tokens; Mistral Small 4 charges $0.60 per 1M output tokens.
Do Claude Haiku 4.5 and Mistral Small 4 offer cache pricing?
Claude Haiku 4.5 discounts cached input to $0.10 per 1M tokens. Mistral Small 4 has no documented cache discount.

Looking for another matchup? See all comparisons.