Claude Sonnet 5 vs Kimi K3.1 Pro
Side-by-side API pricing and Artificial Analysis performance for Claude Sonnet 5 (Anthropic) and Kimi K3.1 Pro (Moonshot AI). Green cells mark the better value in each row.
Prices updated Nov 15, 2026, 10:47 PM UTC · refreshed nightly
| Claude Sonnet 5 Anthropic | Kimi K3.1 Pro Moonshot AI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $2.00 | $2.00 |
| Output $/1M | $10.00 | $10.00 |
| Blended $/1M (3:1) | $4.00 | $4.00 |
| RAG example (30K in / 2K out) | $0.08 | $0.08 |
| Quality & speed | ||
| Intelligence Index | — | 46.5 |
| Coding Index | 71.5 | — |
| Agentic Index | 43.6 | — |
| Output speed (tok/s) | — | — |
| Time to first token | — | — |
| Specs | ||
| Context window | 1M | 1.05M |
| Input modalities | text, image, file | text, image, video |
FAQ
Which is cheaper, Claude Sonnet 5 or Kimi K3.1 Pro?
Claude Sonnet 5 and Kimi K3.1 Pro currently have the same blended API price of $4.00 per 1M tokens.
Which is better for RAG workloads?
Both models cost about $0.08 for a 30K/2K RAG request at current rates. Context windows are 1M (Claude Sonnet 5) and 1.05M (Kimi K3.1 Pro).
Which scores higher on Artificial Analysis benchmarks?
Kimi K3.1 Pro leads on the Artificial Analysis Intelligence Index (46.5 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.