Claude 3 Haiku is cheaper than Qwen Plus 0728 (thinking) at $0.25/M vs $0.4/M input tokens.
| Spec | Claude 3 Haiku | Qwen Plus 0728 (thinking) |
|---|---|---|
| Input price | $0.25/M tokens | $0.4/M tokens |
| Output price | $1.25/M tokens | $4/M tokens |
| Context window | 200K tokens | 1.0M tokens |
| Released | Mar 2024 | Sep 2025 |
Not enough votes to call it. On the specs, Qwen Plus 0728 (thinking) has the edge: bigger model tier, newer, bigger context window.
Claude 3 Haiku costs 3.2x less per token.
Claude 3 Haiku is cheaper on both — 1.6× input, 3.2× output
Qwen Plus 0728 (thinking) uses 34.0x more emoji
Claude 3 Haiku is cheaper than Qwen Plus 0728 (thinking) at $0.25/M vs $0.4/M input tokens.
| Spec | Claude 3 Haiku | Qwen Plus 0728 (thinking) |
|---|---|---|
| Input price | $0.25/M tokens | $0.4/M tokens |
| Output price | $1.25/M tokens | $4/M tokens |
| Context window | 200K tokens | 1.0M tokens |
| Released | Mar 2024 | Sep 2025 |
Not enough votes to call it. On the specs, Qwen Plus 0728 (thinking) has the edge: bigger model tier, newer, bigger context window.
Claude 3 Haiku costs 3.2x less per token.
Claude 3 Haiku is cheaper on both — 1.6× input, 3.2× output
Qwen Plus 0728 (thinking) uses 34.0x more emoji