GPT-6 Luna vs Claude Haiku 5.5: API cost
Standard, cached and batch API prices for GPT-6 Luna (OpenAI) and Claude Haiku 5.5 (Anthropic), and what each costs for your usage.
GPT-6 Luna and Claude Haiku 5.5 have the same standard input and output prices.
- Input $3.00
- Cached input $0.3
- Output $4.50
- Input $3.00
- Cached input $0.3
- Output $4.50
| Token type | GPT-6 Luna | Claude Haiku 5.5 | |
|---|---|---|---|
| Input | $0.10 | $0.10 | Same price |
| Cached input | $0.01 | $0.01 | Same price |
| Output | $0.50 | $0.50 | Same price |
| Batch input | $0.05 | $0.05 | Same price |
| Batch cached input | $0.005 | $0.005 | Same price |
| Batch output | $0.25 | $0.25 | Same price |
GPT-6 Luna: Long prompts are billed at higher long-context rates.
Claude Haiku 5.5: Prompts over 100,000 tokens are billed at a higher rate.
| Workload | GPT-6 Luna | Claude Haiku 5.5 |
|---|---|---|
Support chatbot 2,000 in / 300 out tokens,
1,000 requests a day, 50% cached | $7.80 | $7.80 |
Document summaries 10,000 in / 800 out tokens,
200 requests a day | $8.40 | $8.40 |
Tagging / classifying 400 in / 20 out tokens,
20,000 requests a day | $30.00 | $30.00 |
More comparisons
- GPT-6.1 Sol vs GPT-6 Luna
- GPT-6 Luna vs Gemini 3.5 Flash-Lite
- GPT-6 Luna vs Gemini 3.1 Flash-Lite
- GPT-6 Luna vs Gemini 2.5 Flash
- GPT-6 Luna vs Gemini 2.5 Flash-Lite
- Claude Sonnet 5.5 vs Claude Haiku 5.5
- Claude Haiku 5.5 vs Claude Haiku 4.5
- Claude Haiku 5.5 vs Gemini 3.1 Flash-Lite
Or see GPT-6 Luna pricing, Claude Haiku 5.5 pricing, or compare any two models.
FAQ
Frequently asked questions
Is GPT-6 Luna cheaper than Claude Haiku 5.5?
GPT-6 Luna and Claude Haiku 5.5 have the same standard input and output prices. Based on standard API rates last checked on Oct 13, 2026.
How much do GPT-6 Luna and Claude Haiku 5.5 cost per million tokens?
GPT-6 Luna: $0.10 per million input tokens and $0.50 per million output tokens. Claude Haiku 5.5: $0.10 input and $0.50 output. These are standard rates in USD, before tax, from each provider’s own pricing page.
Which is cheaper with the Batch API?
GPT-6 Luna’s batch rates are $0.05 input and $0.25 output per million tokens (50% off); Claude Haiku 5.5’s batch rates are $0.05 input and $0.25 output per million tokens (50% off).
Does prompt caching change the comparison?
GPT-6 Luna charges $0.01 per million cached input tokens, against $0.10 for normal input; Claude Haiku 5.5 charges $0.01 per million cached input tokens, against $0.10 for normal input. Cache write and storage charges are extra and aren’t included here.