Routin
Loading...
Loading...
Adaptive thinking () is the recommended thinking mode for Opus 4.6 and Sonnet 4.6. Claude dynamically decides when and how much to think. At the default effort level (), Claude will almost always think. At lower effort levels, it may skip thinking for simpler problems.thinking: {type: "adaptive"}high thinking: {type: "enabled"} and are deprecated on Opus 4.6 and Sonnet 4.6. They remain functional but will be removed in a future model release. Use adaptive thinking and the effort parameter to control thinking depth instead. Adaptive thinking also automatically enables interleaved thinking.budget_tokens
A quick read of the model identity, commercial setup, and access footprint.
Published rates, tier transitions, and modality-specific surcharges in the current catalog entry.
| Context Length | Prompt | Output | 5m cache write | 1h cache write | Cache hit |
|---|---|---|---|---|---|
| 0 - 200,000 tokens | ¥1.5000/1M tokens | ¥7.5000/1M tokens | ¥1.8750/1M tokens | ¥3.0000/1M tokens | ¥0.1500/1M tokens |
| >= 200,001 tokens 200K-1M | ¥1.5000/1M tokens | ¥7.5000/1M tokens | ¥1.8750/1M tokens | ¥3.0000/1M tokens | ¥0.1500/1M tokens |
Total tokens usage across all users
Top 10 AI coding agents using this model during the last 15 days.
| # | AI Coding Agents Usage | Total Tokens | Requests | Success rate | Last active |
|---|---|---|---|---|---|
| #1 | Go Language SDK / HTTP client | 11M | 2.6K | 90.6% | 2026-08-01 |
| #2 | ClaudeCode Observed client-provider traffic for this model | 7.64M | 674 | 94.5% | 2026-08-01 |
| #3 | Python |
| 13.1K |
| 142 |
| 36.6% |
| 2026-08-01 |
| #4 | cURL / HTTP Client Language SDK / HTTP client | 574 | 2 | 50.0% | 2026-08-01 |