Claude Haiku vs GPT-5.6 Luna
Two small models with different context budgets. Luna inherits the full GPT-5.6 window; Haiku 4.5 stops at 200K. If you are doing short, high-frequency tasks the difference rarely shows up — pick the one whose family you already use and stop optimising.
| Claude Haiku | GPT-5.6 Luna | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Current release | Haiku 4.5 | GPT-5.6 Luna |
| Tier | Fast & cheap | Fast & cheap |
| Context | 200K | 1M |
| Cost | Low cost | Low cost |
| Modalities | text, vision | text, vision |
| Open weights | No | No |
Cost is a tier, not a quote — providers change prices often. Check Anthropic and OpenAI before you commit. Last updated 2026-08-14.
Which one to pick
Claude HaikuAnthropic · Haiku 4.5
High-volume, low-latency work where speed and cost matter most
Reach for it when- Extraction and classification inside a Claude pipeline
- You want vision on a small model
GPT-5.6 LunaOpenAI
Classification, routing, and extraction at volume
Reach for it when- Long inputs at the cheapest tier
- High-volume routing in an OpenAI stack