Home › Compare › GPT-6 Luna vs Claude Haiku 5.5
GPT-6 Luna vs Claude Haiku 5.5
A straight cost comparison of GPT-6 Luna (OpenAI) and Claude Haiku 5.5 (Anthropic), per 1,000,000 tokens, verified November 2026.
Rate-by-rate comparison
| Metric | GPT-6 Luna | Claude Haiku 5.5 | Winner |
|---|---|---|---|
| Input / 1M | $0.10 | $0.10 | Tie |
| Cached input / 1M | $0.01 | $0.01 | Tie |
| Cache write / 1M | $0.125 | $0.125 | Tie |
| Output / 1M | $0.50 | $0.50 | Tie |
| Context window | 1,050,000 | 200,000 | GPT-6 Luna |
| Batch API | Yes | Yes | Tie |
| Long-context tier | > 272,000 | > 100,000 | — |
For per-token metrics, the lower number wins. For context window and batch support, the higher or broader option wins. A dash means the provider does not publish that rate: a missing cache-write fee means writes are not billed per token, while a missing cached-input rate means cache hits bill at the full input rate.
Blended cost: 1M input + 250K output
| Model | Blended cost | Difference |
|---|---|---|
| GPT-6 Luna | $0.225 | Tie |
| Claude Haiku 5.5 | $0.225 | Tie |
Ten workloads, two bills
The same two models, priced across ten workloads that differ only in their input:output ratio. Nothing else changes — no retries, no system prompt, no middleware.
| Workload | GPT-6 Luna | Claude Haiku 5.5 | Winner |
|---|---|---|---|
| Classification 100K reqs · 500 in / 10 out | $5.50 | $5.50 | Tie |
| Data extraction 10K reqs · 2K in / 200 out | $3 | $3 | Tie |
| Support chat 1K reqs · 4K in / 600 out | $0.70 | $0.70 | Tie |
| Code review 2K reqs · 8K in / 1.5K out | $3.10 | $3.10 | Tie |
| Summarisation 1K reqs · 20K in / 1K out | $2.50 | $2.50 | Tie |
| Agent loop 5K reqs · 12K in / 2K out | $11 | $11 | Tie |
| Translation 500 reqs · 15K in / 15K out | $4.50 | $4.50 | Tie |
| Long-document QA 200 reqs · 120K in / 800 out | $2.48 | $12.08 | GPT-6 Luna |
| Cached RAG 1K reqs · 50K in (45K cached) / 1K out | $1.46 | $1.46 | Tie |
| Nightly batch 10K reqs · 10K in / 2K out | $10 | $10 | Tie |
GPT-6 Luna wins 1 of 10, Claude Haiku 5.5 wins 0 of 10. The winner is set by the token mix, not by the headline rate.
Where the two bills cross over
Both models bill identical input and output rates, so there is no crossover: the two bills are equal at every ratio, and the choice rests entirely on context window, throughput and output quality.
Cost at four scales
The same support-chat workload (4K input, 600 output per request) at four monthly volumes.
| Requests / month | GPT-6 Luna | Claude Haiku 5.5 | Difference |
|---|---|---|---|
| 100 | $0.07 | $0.07 | Tie |
| 1,000 | $0.70 | $0.70 | Tie |
| 10,000 | $7 | $7 | Tie |
| 100,000 | $70 | $70 | Tie |
What caching does to each bill
Caching only helps the part of the prompt that repeats. This is the support-chat workload (1,000 requests, 4,000 input tokens each) with an increasing share of that prompt served from a warm cache, written once on the first request.
| Cached share of the prompt | GPT-6 Luna | Claude Haiku 5.5 | Winner |
|---|---|---|---|
| 0% | $0.70 | $0.70 | Tie |
| 50% | $0.52 | $0.52 | Tie |
| 80% | $0.412 | $0.412 | Tie |
| 95% | $0.358 | $0.358 | Tie |
Both models publish a cached-read rate, so the discount is comparable: GPT-6 Luna reads cache at $0.01 per million, Claude Haiku 5.5 at $0.01.
Which one should you pick?
GPT-6 Luna wins on long-document qa, while Claude Haiku 5.5 wins on none of the ten workloads above.
Beyond price, the two differ on context window (1,050,000 vs 200,000).
Batch mode is available on GPT-6 Luna and Claude Haiku 5.5, which halves the nightly job. Both publish cached-input discounts, so a stable system prompt is worth caching on either.
FAQ
Is GPT-6 Luna cheaper than Claude Haiku 5.5?
No — they are priced identically at $0.225 on a blended 1M-input-plus-250K-output workload, with the same per-token rates. Choose on context window, throughput or output quality instead.
Which handles longer prompts, GPT-6 Luna or Claude Haiku 5.5?
Claude Haiku 5.5 has the larger context window (1,050,000 vs 200,000 tokens). Watch the long-context threshold on GPT-6 Luna and Claude Haiku 5.5: rates rise once input passes it.
Do both models support prompt caching?
GPT-6 Luna bills cached reads at $0.01 per 1M; Claude Haiku 5.5 at $0.01.
Related comparisons
- GPT-6 Luna vs GPT-5.6 Luna
- Claude Haiku 4.5 vs Claude Haiku 5.5
- GPT-6 Luna vs Gemini 3.1 Flash-Lite
- All OpenAI pricing
- All Anthropic pricing