GPT-6 Luna vs Claude Haiku 5.5
Official OpenAI and Anthropic API prices and LMArena scores, checked 2026-11-09. Add up to 2 more models to compare 4.
An even match on price and LMArena tasks.
GPT-6 Luna and Claude Haiku 5.5 have the same list price per token ($0.10 in, $0.50 out per 1M). Claude Haiku 5.5 scores 6 points higher for coding; GPT-6 Luna scores 3 points higher for agent tasks. Across 6 shared LMArena tasks, they split 1 to 1 (4 tied). A medium month (20M input + 5M output tokens) costs $4.50 on GPT-6 Luna and $4.50 on Claude Haiku 5.5.
- Pick GPT-6 Luna if you care most about agent tasks (+3).
- Pick Claude Haiku 5.5 if you care most about coding (+6).
Medium: 20M input + 5M output tokens a month at list price (short-context rate, no caching or batch discounts).
Marked side is better: lower for prices, higher for context and scores. Bars are scaled to the larger of the two.
| Spec | GPT-6 Luna | Claude Haiku 5.5 |
|---|---|---|
| Price per 1M tokens | ||
| Input | $0.10 | $0.10 |
| Cached input | $0.01 | $0.01 |
| Output | $0.50 | $0.50 |
| Blend 3:1 | $0.20 | $0.20 |
| Sample month, medium | $4.50 | $4.50 |
| Context | ||
| Context window | 1.05M tokens | 1M tokens |
| Quality (LMArena, out of 100) | ||
| Coding | 13/100 #27 of 50 | 19/100 #23 of 50 |
| Chat | 0/100 #40 of 51 | 0/100 #45 of 51 |
| Creative writing | 0/100 #35 of 51 | 0/100 #45 of 51 |
| Roleplay and characters | 0/100 #39 of 51 | 0/100 #47 of 51 |
| Reasoning and math | 0/100 #33 of 51 | 0/100 #35 of 51 |
| Vision | 0/100 #28 of 33 | Not ranked |
| Long documents | Not ranked | Not ranked |
| Cheap bulk and agents | 39/100 #18 of 37 | 36/100 #22 of 37 |
| Details | ||
| Provider | OpenAI | Anthropic |
| API model id | gpt-6-luna | claude-haiku-5.5 |
| Notes | Prompts up to 272K. | Prompts up to 100K tokens. Longer prompts cost $0.50 in, $2.50 out. 5-minute cache writes $0.125. |
| Sources | ||
| Last checked | 2026-11-09 | 2026-11-09 |
| Official pricing | OpenAI pricing | Anthropic pricing |
Plans from data checked hourly against each vendor's official pricing page. Vendors state limits in different units, so we quote them as published. Team and enterprise plans are per seat.
API prices in USD per 1M tokens from each provider's official pricing page. Blend 3:1 = (3 x input + output) / 4. Sample month = stated input and output tokens at the list price, no caching. Quality: relative score out of 100 on each LMArena leaderboard (100 = top model we price on that board, n/a = not ranked there), data licensed CC BY 4.0. See how we pick.
Where each one ranks on LMArena
Relative score out of 100 on each leaderboard (100 = the top model we price there), with the rank among the models from our API price table that appear on that board.
- Coding (Code Arena): GPT-6 Luna #27 of 50 (13/100), Claude Haiku 5.5 #23 of 50 (19/100)
- Chat (Text Arena): GPT-6 Luna #40 of 51 (0/100), Claude Haiku 5.5 #45 of 51 (0/100)
- Creative writing (Text Arena creative writing): GPT-6 Luna #35 of 51 (0/100), Claude Haiku 5.5 #45 of 51 (0/100)
- Roleplay and characters (Text Arena multi-turn): GPT-6 Luna #39 of 51 (0/100), Claude Haiku 5.5 #47 of 51 (0/100)
- Reasoning and math (Text Arena math): GPT-6 Luna #33 of 51 (0/100), Claude Haiku 5.5 #35 of 51 (0/100)
- Vision (Vision Arena): GPT-6 Luna #28 of 33 (0/100), Claude Haiku 5.5 not ranked
- Long documents (Document Arena): GPT-6 Luna not ranked, Claude Haiku 5.5 not ranked
- Cheap bulk and agents (Agent Arena): GPT-6 Luna #18 of 37 (39/100), Claude Haiku 5.5 #22 of 37 (36/100)
Pricing details from the official pages
GPT-6 Luna lists $0.10 input, $0.50 output, $0.01 cached input per 1M tokens on OpenAI pricing. Claude Haiku 5.5 lists $0.10 input, $0.50 output, $0.01 cached input per 1M tokens on Anthropic pricing. Prices checked 2026-11-09.
- GPT-6 Luna: Prompts up to 272K.
- Claude Haiku 5.5: Prompts up to 100K tokens. Longer prompts cost $0.50 in, $2.50 out. 5-minute cache writes $0.125.
Sample monthly bill at list price, no caching: Light (2M input + 0.5M output tokens): $0.45 vs $0.45. Medium (20M input + 5M output tokens): $4.50 vs $4.50. Heavy (200M input + 50M output tokens): $45 vs $45.
FAQ
Is GPT-6 Luna cheaper than Claude Haiku 5.5?
They have the same list price: $0.10 input and $0.50 output per 1M tokens.
Which is better for coding, GPT-6 Luna or Claude Haiku 5.5?
On LMArena's Code Arena GPT-6 Luna scores 13/100 (#27 of 50) and Claude Haiku 5.5 19/100 (#23 of 50), so Claude Haiku 5.5 is ahead by 6 points.
Which has the bigger context window?
GPT-6 Luna: 1.05M tokens. Claude Haiku 5.5: 1M tokens. Long prompts can cost more; see the pricing notes above.
How much do GPT-6 Luna and Claude Haiku 5.5 cost per month?
Light (2M input + 0.5M output tokens): $0.45 vs $0.45. Medium (20M input + 5M output tokens): $4.50 vs $4.50. Heavy (200M input + 50M output tokens): $45 vs $45. Pick your own token counts in the plan vs API calculator.
Where do these numbers come from?
Prices come from each provider's official pricing page, checked daily. Quality is the relative score on the LMArena leaderboard dataset, licensed CC BY 4.0. Where a model is not ranked we show n/a.
Sources
Related
- OpenAI vs Anthropic API pricing
- Cheapest LLM APIs, compared
- OpenAI API pricing, every model
- Anthropic API pricing, every model
- Claude Haiku 5.5 vs Gemini 3.8 Flash
- GPT-6 Luna vs Gemini 3.8 Flash
- DeepSeek V4.1 Flash vs GPT-6 Luna
- DeepSeek V4.1 Flash vs Claude Haiku 5.5
- Claude Sonnet 5.5 vs Claude Haiku 5.5
- AI API prices, all models