Claude Haiku 4.5 vs GPT-5.6 Luna: pricing and benchmarks
GPT-5.6 Luna is 80% cheaper on input tokens ($0.20 vs $1.00 per 1M). GPT-5.6 Luna is 76% cheaper on output tokens ($1.20 vs $5.00 per 1M). On our document Q&A workload (50,000 questions a month), GPT-5.6 Luna costs $116.00 a month versus $550.00 for Claude Haiku 4.5, 79% less. GPT-5.6 Luna scores 156.3 on the Epoch Capabilities Index vs 142.4 for Claude Haiku 4.5.
Prices verified September 14, 2026.
Which should you choose?
GPT-5.6 Luna scores 156.3 on the Epoch Capabilities Index vs 142.4 for Claude Haiku 4.5.
GPT-5.6 Luna costs $0.45 per 1M tokens (3:1 input-to-output mix) vs $2.00 for Claude Haiku 4.5, 78% less.
GPT-5.6 Luna delivers equal or higher overall capability for 78% less.
Pricing and specs
| Claude Haiku 4.5 | GPT-5.6 Luna | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| API model ID | claude-haiku-4-5-20251001 | gpt-5.6-luna |
| Input / 1M tokens | $1.00 | $0.20 |
| Cached input / 1M tokens | $0.10 | $0.02 |
| Output / 1M tokens | $5.00 | $1.20 |
| Long-context rates | — | $0.40 in / $1.80 out on long-context requests |
| Context window | 200K tokens | 1.05M tokens |
| Max output | 64K tokens | 128K tokens |
| Batch discount | 50% off | 50% off |
Benchmarks
| Claude Haiku 4.5 | GPT-5.6 Luna | |
|---|---|---|
| Epoch Capabilities Index | 142.4 | 156.3 |
| GPQA Diamond· Science reasoning | 61.6% | 88.8% |
| FrontierMath (Tiers 1–3)· Advanced math | — | 82.1% |
| SimpleQA Verified· Factual accuracy | 13.2% | 41.0% |
| ARC-AGI-2· Abstract reasoning | 4.0% | 59.5% |
| DeepSWE· Coding | — | 67.2% |
| APEX-Agents· Agentic work | 8.9% | — |
Source: Epoch AI, best recorded result per model (CC BY 4.0). A dash means no published score. See all benchmarks
Monthly cost for real workloads
| Workload | Claude Haiku 4.5 | GPT-5.6 Luna | Difference |
|---|---|---|---|
Support chatbot 100,000 replies a month, ~1,500 input tokens (system prompt + history) and ~400 output tokens each. | $350.00 | $78.00 | GPT-5.6 Luna 78% cheaper |
Document Q&A (RAG) 50,000 questions a month with ~8,000 tokens of retrieved context and ~600 output tokens each. | $550.00 | $116.00 | GPT-5.6 Luna 79% cheaper |
Coding agent 10,000 agent steps a month, ~40,000 input tokens each (70% read from the prompt cache) and ~2,000 output tokens. | $248.00 | $53.60 | GPT-5.6 Luna 78% cheaper |
Estimates use standard list prices and ignore cache-write surcharges. Different tokenizers can count the same text differently, so test with your own prompts.
Claude Haiku 4.5 vs GPT-5.6 Luna cost calculator
- $116.00/mo$0.0023 / request
- Claude Haiku 4.5Anthropic$550.00/mo$0.01 / request
Standard-tier list prices. Long-context rates apply automatically where the provider publishes a threshold. Excludes cache-write surcharges, taxes, batch and volume discounts.
Claude Haiku 4.5 pricing notes
Anthropic’s fastest model, with near-frontier intelligence.
- Cache writes cost $1.25 (5-minute cache) or $2 (1-hour cache) per 1M tokens.
- Uses Anthropic’s previous tokenizer.
GPT-5.6 Luna pricing notes
The GPT-5.6 model optimized for cost-sensitive, high-volume workloads.
- Cache writes are billed at $0.25 per 1M tokens.
- Fast mode costs 2x the standard rate; Flex costs half.
Frequently asked questions
- Is Claude Haiku 4.5 cheaper than GPT-5.6 Luna?
- GPT-5.6 Luna is 80% cheaper on input tokens ($0.20 vs $1.00 per 1M). GPT-5.6 Luna is 76% cheaper on output tokens ($1.20 vs $5.00 per 1M). On our document Q&A workload (50,000 questions a month), GPT-5.6 Luna costs $116.00 a month versus $550.00 for Claude Haiku 4.5, 79% less.
- Which is more capable, Claude Haiku 4.5 or GPT-5.6 Luna?
- GPT-5.6 Luna scores 156.3 on the Epoch Capabilities Index vs 142.4 for Claude Haiku 4.5.
- How much does Claude Haiku 4.5 cost per 1M tokens?
- Claude Haiku 4.5 costs $1.00 per 1M input tokens and $5.00 per 1M output tokens, and $0.10 per 1M cached input tokens on Anthropic’s standard tier.
- How much does GPT-5.6 Luna cost per 1M tokens?
- GPT-5.6 Luna costs $0.20 per 1M input tokens and $1.20 per 1M output tokens, and $0.02 per 1M cached input tokens on OpenAI’s standard tier.
- Which has the larger context window, Claude Haiku 4.5 or GPT-5.6 Luna?
- GPT-5.6 Luna has the larger context window: 1.05M tokens versus 200K for Claude Haiku 4.5.