Skip to main content
AI Choice EngineAI Choice Engine

Model comparison

GPT-5.4 Nano vs GPT-5.6 Luna

Two OpenAI tiers compared on the figures that decide which one a workload actually needs.

Catalog record checked September 3, 2026Individual provider fields may changeEvidence confidence: High — see receipts below

OpenAI

GPT-5.4 Nano

Budget

vs

OpenAI

GPT-5.6 Luna

Budget

AI model capability comparison
SpecificationGPT-5.4 NanoGPT-5.6 Luna
ProviderOpenAIOpenAI
TierBudgetBudget
Context window400KWinner: 1.05M
Max output128K128K
Input / 1M tokens$0.20$0.20
Output / 1M tokens$1.25Winner: $1.20
WeightsClosedClosed
ParametersNot disclosedUnverifiedcheapest GPT-5.6 tier
Reasoning levelsnone, low, medium, highnone, low, medium, high
Modalitiestext, imagetext, image
API model idgpt-5.4-nanogpt-5.6-luna
ReleasedMarch 17, 2026July 9, 2026
Artificial Analysis Intelligence Index [high] (2026-08-14)40Winner: 47
SWE-bench Verified (2026-09-01)Not verifiedUnverified93
Terminal-Bench 2.1 (2026-07-09)Not verifiedUnverified84.7
LiveBench (2026-09-05)Not verifiedUnverified73.6

Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.

Benchmark receipts

  • 2026-09-05: LiveBench official leaderboard (benchmark-owned), max effortContamination-resistant general capability across reasoning, coding, math, data analysis, and language, with monthly question refreshes. Comparability: comparable with caveat — Rolling question set: observations months apart measure different question mixes. Record the measurement date and compare within ~1 month windows.
  • 2026-09-01: vals.ai SWE-bench Verified leaderboard (independent, mini-swe-agent bash-only) (independent; OpenAI did not report SWE-bench Verified for the GPT-5.6 family)Real GitHub issue resolution: does the model's patch pass the hidden tests. Comparability: comparable with caveat — Post-audit vendor claims and pre-audit scores sit on different task trust levels; scaffolding (agent harness, compute budget) also dominates results. Never aggregate across scaffolds.
  • 2026-08-14: Artificial AnalysisComposite index blending reasoning, knowledge, and coding evals into one 0–100 score. Comparability: directly comparable — AA occasionally rebaselines the index scale between snapshots — a score captured on one date is only comparable to same-snapshot scores (check measuredAt).
  • 2026-07-09: OpenAI GPT-5.6 announcement (vendor; chart transcribed by Vellum)Agentic terminal work: multi-step tasks executed in a sandboxed shell environment. Comparability: comparable with caveat — Scores across Terminal-Bench major versions (v1 vs v2) are NOT comparable; harness configuration (container, time limits) also shifts results.

Pricing tiers: GPT-5.4 Nano: Standard $0.20/$1.25 per MTok; cached input $0.02/MTok; batch $0.10/$0.625. · GPT-5.6 Luna: Launch list was $1/$6; cut to $0.20/$1.20 on 2026-07-30. Cached input $0.02/MTok; batch $0.10/$0.60.

BudgetRecord checked September 3, 2026

GPT-5.4 Nano

GPT-5.4 Nano is OpenAI's cheapest small tier for classification and extraction at $0.20/$1.25.

Best for

  • Classification
  • Summarisation
  • High-volume chat

Watch out

Smallest tier; not for hard reasoning or coding.

BudgetRecord checked September 3, 2026

GPT-5.6 Luna

GPT-5.6 Luna is OpenAI's cheapest tier — roughly 1/25 of Opus 5-class input cost, suitable where quality requirements are modest.

Best for

  • Classification
  • High-volume chat
  • Latency-sensitive pipelines

Watch out

Smallest GPT-5.6 tier; verify quality holds before routing frontier work to it.

When the cheaper one wins

GPT-5.6 Luna is cheaper on output at $1.20 per million tokens against $1.25 for GPT-5.4 Nano — about 1.0×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. These are standard-tier API rates, excluding batch and cache discounts.

Run the model picker

Evidence confidence: High

How strong and complete the evidence behind this comparison is — not a prediction of which model is better.

  • Pricing verified on both sidesInput and output rates are verified for both models.
  • 4/5 core specs verified on both sidesNot published for at least one side: parameter count.
  • 1 shared named benchmark with differing scoresMeasured on: Artificial Analysis Intelligence Index.
  • Verified within the last 90 daysNewest catalog check was 8 days ago.
  • Both models carry source citationsEach side has at least two catalog sources on record.

Source receipts

Each catalog figure was checked against the provider or an independent second source on the date shown.

Common questions

GPT-5.4 Nano vs GPT-5.6 Luna

Answered from the verified figures on this page rather than general guidance.

Is GPT-5.4 Nano or GPT-5.6 Luna cheaper for input?

Both cost $0.20 per million input tokens at standard rates, so input price is not a deciding factor between them.

Is GPT-5.4 Nano or GPT-5.6 Luna cheaper for output?

GPT-5.6 Luna is cheaper at $1.20 per million output tokens, against $1.25 for GPT-5.4 Nano — roughly 1.0× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; GPT-5.4 Nano has tiered pricing: Standard $0.20/$1.25 per MTok; cached input $0.02/MTok; batch $0.10/$0.625. GPT-5.6 Luna has tiered pricing: Launch list was $1/$6; cut to $0.20/$1.20 on 2026-07-30. Cached input $0.02/MTok; batch $0.10/$0.60.

Which has the larger context window, GPT-5.4 Nano or GPT-5.6 Luna?

GPT-5.6 Luna accepts 1.05M tokens against 400K for GPT-5.4 Nano. This only matters if you routinely send very long documents or large codebases.

Do GPT-5.4 Nano and GPT-5.6 Luna support the same reasoning levels?

Yes — both accept the same effort settings: "none", "low", "medium", "high". Higher effort costs more and takes longer, so start low and raise it only where output quality actually improves.

Should I use GPT-5.4 Nano or GPT-5.6 Luna?

Both sit in the budget tier, so the choice usually comes down to price and context rather than capability. GPT-5.4 Nano suits classification; GPT-5.6 Luna suits classification.

Next step

Choosing between them

The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.

  • Context: GPT-5.6 Luna takes 1.05M against 400K for GPT-5.4 Nano — only decisive if your prompts approach the smaller window.
  • Measured capability: GPT-5.6 Luna leads Artificial Analysis Intelligence Index 47 to 40 (measured 2026-08-14).

Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.