GPT-5.6 Luna vs GPT-5.4 nano
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by OpenAI
|
by OpenAI
|
|---|---|---|
| Overview | ||
| Status | Current mid tier | Current budget |
| Released | Jul 9, 2026 | Mar 17, 2026 |
| Pricing per million tokens | ||
| Input | $0.200/Mtok | $0.200/Mtok |
| Output | $1.20/Mtok | $1.25/Mtok |
| Blended avg | $0.700/Mtok | $0.725/Mtok |
| Cached input | $0.020/Mtok | $0.020/Mtok |
| Specifications | ||
| Context window | 1M tokens | 400K tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
textimage
|
textimage
|
| Benchmarks sources: Vellum LLM Leaderboard / Artificial Analysis (via BenchLM), LMSYS Chatbot Arena (snapshot via BenchLM), OpenAI model card (no tools) | ||
| Independent composite scores measured for both models — each on its own scale | ||
| AA Intelligence Index | 51.2 | 38.2 |
| AA Agentic Index | 45.6 | — |
| AA-Omniscience Index (−100–100) | -11.2 | — |
| GDPval-AA v2 | 1581.9 ELO | — |
| LMSYS Chatbot Arena | — | 1466 ELO |
| Per-benchmark results no per-benchmark score is published for both models — the composites above are what compares them | ||
| Avg benchmark score | 90.7 | — |
| Perf / dollar | 25.9 | — |
| GPQA Diamond | 92.3 | — |
| SWE-Bench Verified | 93 | — |
| Terminal-Bench 2.1 | 84.3 | — |
| Humanity's Last Exam | — | 24.3 vendor |
| HumanEval | 93 | — |
| Providers | ||
| Available from |
OpenAI — $0.200/$1.20/Mtok
|
OpenAI — $0.200/$1.25/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | GPT-5.6 Luna | GPT-5.4 nano | Savings |
|---|---|---|---|
| 1M tokens | $0.7 | $0.73 | $0.03 (4.1%) |
| 10M tokens | $7 | $7.25 | $0.25 (3.4%) |
| 100M tokens | $70 | $72.5 | $2.5 (3.4%) |
| 1000M tokens | $700 | $725 | $25 (3.4%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $0.700/Mtok blended vs $0.725 — 3.4% less on the same 50/50 token mix
- you need the longer context: 1M tokens vs 400K (2.6×)
- this pairing gives GPT-5.4 nano 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 1, 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 |
| GPT-5.4 nano | 0 | — no move | Stable since we began tracking — no change recorded |
The cheaper option here — GPT-5.6 Luna costs $0.700/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.
GPT-5.4 nano by OpenAI costs $0.200/Mtok input and $1.25/Mtok output, with a 400K-token context window. It supports text, image input.
On a blended cost basis, GPT-5.6 Luna is 3.4% cheaper than GPT-5.4 nano. It also has a larger context window.
The two aren't directly comparable on average benchmark score: GPT-5.6 Luna has published per-benchmark results, while GPT-5.4 nano does not yet — it is measured today on independent composites (see the table above).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.