Claude Sonnet 5 vs Hy3 preview
Side-by-side API pricing and Artificial Analysis performance for Claude Sonnet 5 (Anthropic) and Hy3 preview (Tencent). Green cells mark the better value in each row.
Prices updated Nov 14, 2026, 3:43 PM UTC · refreshed nightly
| Claude Sonnet 5 Anthropic | Hy3 preview Tencent | |
|---|---|---|
| Pricing | ||
| Input $/1M | $2.00 | $0.18 |
| Output $/1M | $10.00 | $0.60 |
| Blended $/1M (3:1) | $4.00 | $0.285 |
| RAG example (30K in / 2K out) | $0.08 | $0.0066 |
| Quality & speed | ||
| Intelligence Index | — | — |
| Coding Index | 71.5 | 58.8 |
| Agentic Index | 43.6 | 24.1 |
| Output speed (tok/s) | — | — |
| Time to first token | — | — |
| Specs | ||
| Context window | 1M | 262K |
| Input modalities | text, image, file | text |
FAQ
Which is cheaper, Claude Sonnet 5 or Hy3 preview?
Hy3 preview has the lower blended API price at $0.285 per 1M tokens (3:1 input:output mix), versus $4.00 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), Hy3 preview costs about $0.0066 per request versus $0.08. Also compare context windows: Claude Sonnet 5 offers 1M and Hy3 preview offers 262K.
Which scores higher on Artificial Analysis benchmarks?
Intelligence Index scores are unavailable or tied for these two models. Compare coding index, speed, and price on this page to decide.