Claude 3 Haiku vs GPT-6 Luna
Price, context window & benchmark comparison
VS
Compare different models
Verdict: GPT-6 Luna is 2.5× cheaper than Claude 3 Haiku on a typical 3:1 input/output mix. GPT-6 Luna has the larger context window (1.1M vs 200K).
| Claude 3 Haiku | GPT-6 Luna | |
|---|---|---|
| Input price / 1M | $0.25 | $0.10 |
| Output price / 1M | $1.25 | $0.50 |
| Blended price (3:1) | $0.50 | $0.20 |
| Cached input / 1M | $0.03 | $0.01 |
| Context window | 200K | 1.1M |
| Max output | 4K | 128K |
| Intelligence index | — | 37.3 |
| Coding index | — | — |
| Providers | — | 7 |
| Best provider uptime (30m) | — | 100.0% |
| Vision input | Yes | Yes |
| Reasoning | No | Yes |
| Tool calling | Yes | Yes |
| Released | 2024-03-13 | 2026-09-22 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, Claude 3 Haiku or GPT-6 Luna?
GPT-6 Luna is 2.5× cheaper than Claude 3 Haiku on a typical 3:1 input/output mix.
Claude 3 Haiku vs GPT-6 Luna: which has a bigger context window?
Claude 3 Haiku: 200,000 tokens. GPT-6 Luna: 1,050,000 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: Claude 3 Haiku ≈ $1,125, GPT-6 Luna ≈ $450.00.
More comparisons
Claude 3 Haiku vs GLM 5.3 PrimeClaude 3 Haiku vs Qwen3.8 Max PrimeClaude 3 Haiku vs Command A+Claude 3 Haiku vs GPT-6 Luna ProClaude 3 Haiku vs GPT-6 Sol ProClaude 3 Haiku vs GPT-6 SolClaude 3 Haiku vs Claude Opus 5.5Claude 3 Haiku vs MiMo-V2.6-Pro-UltraSpeedClaude 3 Haiku vs MiMo-V2.6-FlashClaude 3 Haiku vs Grok 4.7Claude 3 Haiku vs Qwen3.8 Omni FlashClaude 3 Haiku vs GLM 5.3 FlashXClaude 3 Haiku vs DeepSeek V4.1 FlashClaude 3 Haiku vs GPT-6 AstraClaude 3 Haiku vs GPT-6 Astra ProClaude 3 Haiku vs Qwen3.8 Max (0902)GPT-6 Luna vs GLM 5.3 PrimeGPT-6 Luna vs Qwen3.8 Max PrimeGPT-6 Luna vs Command A+GPT-6 Luna vs GPT-6 Luna ProGPT-6 Luna vs GPT-6 Sol ProGPT-6 Luna vs GPT-6 SolGPT-6 Luna vs Claude Opus 5.5GPT-6 Luna vs MiMo-V2.6-Pro-UltraSpeed