AiCostCompare

Claude Haiku 4.5 vs MiMo-V2.5

Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and MiMo-V2.5 (Xiaomi). Green cells mark the better value in each row.

Prices updated Jul 22, 2026, 1:41 AM UTC · refreshed hourly

Claude Haiku 4.5

Anthropic

MiMo-V2.5

Xiaomi

Pricing
Input $/1M$1.00$0.14
Output $/1M$5.00$0.28
Blended $/1M (3:1)$2.00$0.175
RAG example (30K in / 2K out)$0.04$0.00476
Quality & speed
Intelligence Index29.637.2
Coding Index43.956.8
Agentic Index16.423.7
Output speed (tok/s)63
Time to first token3.40s
Specs
Context window200K1.05M
Input modalitiestext, image, filetext, audio, image, video

FAQ

Which is cheaper, Claude Haiku 4.5 or MiMo-V2.5?

MiMo-V2.5 has the lower blended API price at $0.175 per 1M tokens (3:1 input:output mix), versus $2.00 for the other model. Prices are live from OpenRouter and refresh about hourly.

Which is better for RAG workloads?

For a typical RAG request (30K input / 2K output tokens), MiMo-V2.5 costs about $0.00476 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and MiMo-V2.5 offers 1.05M.

Which scores higher on Artificial Analysis benchmarks?

MiMo-V2.5 leads on the Artificial Analysis Intelligence Index (37.2 vs 29.6). Check coding and agentic indices on this page for workload-specific tradeoffs.