AiCostCompare

Claude Haiku 4.5 vs Mistral Large 4

Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and Mistral Large 4 (Mistral). Green cells mark the better value in each row.

Prices updated Nov 18, 2026, 1:06 PM UTC · refreshed nightly

Claude Haiku 4.5

Anthropic

Mistral Large 4

Mistral

Pricing
Input $/1M$1.00$0.70
Output $/1M$5.00$2.10
Blended $/1M (3:1)$2.00$1.05
RAG example (30K in / 2K out)$0.04$0.0252
Quality & speed
Intelligence Index7.426.1
Coding Index43.9—
Agentic Index8—
Output speed (tok/s)——
Time to first token——
Specs
Context window200K1.05M
Input modalitiestext, image, filetext, image

FAQ

Which is cheaper, Claude Haiku 4.5 or Mistral Large 4?

Mistral Large 4 has the lower blended API price at $1.05 per 1M tokens (3:1 input:output mix), versus $2.00 for the other model. Prices are live from OpenRouter and refresh nightly.

Which is better for RAG workloads?

For a typical RAG request (30K input / 2K output tokens), Mistral Large 4 costs about $0.0252 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and Mistral Large 4 offers 1.05M.

Which scores higher on Artificial Analysis benchmarks?

Mistral Large 4 leads on the Artificial Analysis Intelligence Index (26.1 vs 7.4). Check coding and agentic indices on this page for workload-specific tradeoffs.