docai.cc

Claude Sonnet 4.5 (latest) vs Claude Haiku 4.5 (latest)

30-second takeaway

  • Claude Haiku 4.5 (latest) has the cheaper input: $1 vs $3 (per 1M tokens, 67% less)
  • Same context window (200K tokens)
Claude Sonnet 4.5 (latest)
Anthropic
Claude Haiku 4.5 (latest)
Anthropic
Input$3$1
Output$15$5
Context200K200K
More specs (max output / capabilities)
max output64,00064,000
Reasoning✓ Yes✓ Yes
Tool calls✓ Yes✓ Yes
Open weights— No— No
中转站最低报价(输入价)—vs—实测榜 →

Prices are official/data-source rates (per 1M tokens), not what relays actually charge — relay prices vary with discounts and group multipliers. See methodology.

Other comparisons involving them

Relay Tests

Uptime, latency, risk signals, 7-day success rate

Relay Tests