Claude Opus 4.6 vs MiniMax M2-her
Side-by-side API pricing and Artificial Analysis performance for Claude Opus 4.6 (Anthropic) and MiniMax M2-her (MiniMax). Green cells mark the better value in each row.
Prices updated Jul 22, 2026, 3:54 AM UTC · refreshed hourly
| Claude Opus 4.6 Anthropic | MiniMax M2-her MiniMax | |
|---|---|---|
| Pricing | ||
| Input $/1M | $5.00 | $0.30 |
| Output $/1M | $25.00 | $1.20 |
| Blended $/1M (3:1) | $10.00 | $0.525 |
| RAG example (30K in / 2K out) | $0.2 | $0.0114 |
| Quality & speed | ||
| Intelligence Index | 37.8 | — |
| Coding Index | — | — |
| Agentic Index | — | — |
| Output speed (tok/s) | 57 | — |
| Time to first token | 1.85s | — |
| Specs | ||
| Context window | 1M | 66K |
| Input modalities | text, image, file | text |
FAQ
Which is cheaper, Claude Opus 4.6 or MiniMax M2-her?
MiniMax M2-her has the lower blended API price at $0.525 per 1M tokens (3:1 input:output mix), versus $10.00 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), MiniMax M2-her costs about $0.0114 per request versus $0.2. Also compare context windows: Claude Opus 4.6 offers 1M and MiniMax M2-her offers 66K.
Which scores higher on Artificial Analysis benchmarks?
Claude Opus 4.6 leads on the Artificial Analysis Intelligence Index (37.8 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.