Claude 3 Haiku is cheaper than GPT-5.3-Codex at $0.25/M vs $1.75/M input tokens.
| Spec | Claude 3 Haiku | GPT-5.3-Codex |
|---|---|---|
| Input price | $0.25/M tokens | $1.75/M tokens |
| Output price | $1.25/M tokens | $14/M tokens |
| Context window | 200K tokens | 400K tokens |
| Released | Mar 2024 | Feb 2026 |
Not enough votes to call it. On the specs, GPT-5.3-Codex has the edge: bigger model tier, newer, bigger context window.
Claude 3 Haiku costs 11x less per token.
Claude 3 Haiku is cheaper on both — 7.0× input, 11× output
GPT-5.3-Codex uses 15.8x more emoji
Claude 3 Haiku is cheaper than GPT-5.3-Codex at $0.25/M vs $1.75/M input tokens.
| Spec | Claude 3 Haiku | GPT-5.3-Codex |
|---|---|---|
| Input price | $0.25/M tokens | $1.75/M tokens |
| Output price | $1.25/M tokens | $14/M tokens |
| Context window | 200K tokens | 400K tokens |
| Released | Mar 2024 | Feb 2026 |
Not enough votes to call it. On the specs, GPT-5.3-Codex has the edge: bigger model tier, newer, bigger context window.
Claude 3 Haiku costs 11x less per token.
Claude 3 Haiku is cheaper on both — 7.0× input, 11× output
GPT-5.3-Codex uses 15.8x more emoji