GPT-5.6 Luna vs Claude Haiku 4.5
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by OpenAI
|
by Anthropic
|
|---|---|---|
| Overview | ||
| Status | Current mid tier | Current budget |
| Released | Jul 9, 2026 | Oct 15, 2025 |
| Pricing per million tokens | ||
| Input | $0.200/Mtok | $1.00/Mtok |
| Output | $1.20/Mtok | $5.00/Mtok |
| Blended avg | $0.450/Mtok | $2.00/Mtok |
| Cached input | $0.020/Mtok | $0.100/Mtok |
| Specifications | ||
| Context window | 1M tokens | 200K tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
textimage
|
textimage
|
| Benchmarks source: Vellum LLM Leaderboard | ||
| Avg benchmark score | 90.7 | 65.5 |
| Perf / dollar | 201.6 | 32.8 |
| GPQA Diamond | 92.3 | 73 |
| Terminal-Bench 2.1 | 84.3 | 27.5 |
| HumanEval | 93 | 73.3 |
| SWE-Bench Verified | 93 | — |
| MCP Atlas | — | 40.2 |
| AIME 2025 | — | 96.3 |
| MMMLU | — | 83 |
| MATH 500 | — | 78 vendor |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | 52.3 | 29.9 |
| AA Agentic Index | 46.9 | 16.5 |
| AA-Omniscience Index (−100–100) | -10.3 | -4.4 |
| GDPval-AA v2 | 1569.1 ELO | — |
| LMSYS Chatbot Arena | — | 1413.2 ELO |
| Providers | ||
| Available from |
OpenAI — $0.200/$1.20/Mtok
|
Anthropic — $1.00/$5.00/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | GPT-5.6 Luna | Claude Haiku 4.5 | Savings |
|---|---|---|---|
| 1M tokens | $0.45 | $2 | $1.55 (77.5%) |
| 10M tokens | $4.5 | $20 | $15.5 (77.5%) |
| 100M tokens | $45 | $200 | $155 (77.5%) |
| 1000M tokens | $450 | $2000 | $1550 (77.5%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $0.450/Mtok blended vs $2.00 — 77.5% less on the same 50/50 token mix
- you need the longer context: 1M tokens vs 200K (5.3×)
- raw capability matters more than price: 90.7 vs 65.5 average benchmark score
- this pairing gives Claude Haiku 4.5 no edge on price, context, cache discount, or measured performance — pick it only for qualitative fit (ecosystem, compliance, model behavior on your prompts)
Price movement
recorded changes since we began tracking each model · last checked Aug 28, 2026| Model | Changes | Latest move | Old → new $/M |
|---|---|---|---|
| GPT-5.6 Luna | 1 | price cut on Aug 1, 2026 | $1/$6 → $0.2/$1.2/Mtok |
| Claude Haiku 4.5 | 0 | — no move | Stable since we began tracking — no change recorded |
The cheaper option here — GPT-5.6 Luna costs $0.450/Mtok blended on OpenAI.
Summary
GPT-5.6 Luna by OpenAI costs $0.200/Mtok input and $1.20/Mtok output, with a 1M-token context window. It supports text, image input.
Claude Haiku 4.5 by Anthropic costs $1.00/Mtok input and $5.00/Mtok output, with a 200K-token context window. It supports text, image input.
On a blended cost basis, GPT-5.6 Luna is 77.5% cheaper than Claude Haiku 4.5.It also has a larger context window.
On benchmarks, GPT-5.6 Luna scores higher (90.7 vs 65.5) on average. In terms of value, GPT-5.6 Luna has better performance per dollar (201.6 vs 32.8).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.