Claude Sonnet 4.6 is Anthropic best coding model and the recommended choice for most development workflows. At $3/$15 per MTok, it offers an excellent balance of capability and cost. Sonnet 4.6 powers most Claude Code sessions and excels at agentic coding, instruction following, and nuanced writing tasks.
| Benchmark | Score |
|---|---|
| Arena Elo (LMArena) | 1355 |
| Context Window | 200K |
| Price (input/output) | $3/$15 |
Daily tokens (prompt + completion) routed to Claude Sonnet 4.6 on OpenRouter, from Jun 20 to Sep 2, from our own stored daily snapshots. Reflects OpenRouter API demand only. See all models →
| Date | Prompt /MTok | Completion /MTok |
|---|---|---|
| 2026-08-07 | $3 → $1.5 | $15 → $7.5 |
Changes observed across 76 daily OpenRouter catalog snapshots since Jun 19, 2026.