Direct API pricing comparison
GPT-5.6 Luna vs Claude Haiku 4.5
Compare current direct API token prices and estimated monthly workload costs for GPT-5.6 Luna and Claude Haiku 4.5.
2direct models
Pricing only.GPT-5.6 Luna is cheaper in 4 of 4 comparable standard workload presets below. This is a pricing comparison only; it does not rank model quality.
| Model | Input | Cached | Output | Context | Max output | Source |
|---|---|---|---|---|---|---|
GPT-5.6 LunaOpenAI · Direct API | $0.2 | $0.02 | $1.2 | 1.05M | 128K | Direct ↗ |
Claude Haiku 4.5Anthropic · Direct API | $1 | $0.1 | $5 | 200K | 64K | Direct ↗ |
Same workload, different API bill
These four presets use 30 active days, standard direct rates, no retries, no reasoning-token add-on, no cache writes, and the cached-input percentage shown in each row.
| Standard workload | GPT-5.6 Luna | Claude Haiku 4.5 | Lower monthly estimate |
|---|---|---|---|
| Chat10,000/day · 2,000 in · 500 out · 25% cached | $273 | $1,215 | GPT-5.6 Luna by $942 / mo |
| Coding2,000/day · 12,000 in · 1,800 out · 55% cached | $202.32 | $903.6 | GPT-5.6 Luna by $701.28 / mo |
| Agent1,200/day · 32,000 in · 2,500 out · 65% cached | $203.62 | $928.08 | GPT-5.6 Luna by $724.46 / mo |
| Documents400/day · 180,000 in · 2,000 out · 15% cached | $402.48 | $1,988.4 | GPT-5.6 Luna by $1,585.92 / mo |
The main calculator includes batch mode, long-context rules, retries, reasoning tokens, cache writes, and other model-specific pricing logic that a static comparison cannot fully capture.