Migrating from gpt-5.4-nano to gpt-6-luna

What changes when you move from gpt-5.4-nano to gpt-6-luna: input price −50%, output price −60%, context window 400,000 → 1,050,000 tokens.

From: gpt-5.4-nano
Status: Deprecated
Shutdown: Apr 1, 2027
Time left: 168 days

To: gpt-6-luna
Status: Active
Shutdown: none announced
Time left: —

Prices

USD per 1M tokens, standard tier

Type	gpt-5.4-nano	gpt-6-luna	Change
Input	$0.20first seen October 1, 2026 · source	$0.10first seen October 1, 2026 · source	−50%
Cached input	$0.02first seen October 1, 2026 · source	$0.01first seen October 1, 2026 · source	−50%
Output	$1.25first seen October 1, 2026 · source	$0.50first seen October 1, 2026 · source	−60%

At 1M input and 250K output tokens a month: $0.5125 on gpt-5.4-nano, $0.225 on gpt-6-luna (−56.1%).

Other tiers, prompt-size bands and modalities are on each model's page.

Limits

Tokens

Limit	gpt-5.4-nano	gpt-6-luna	Change
Context window	400,000 tokensin place when tracking began (October 7, 2026) · source	1,050,000 tokensin place when tracking began (October 7, 2026) · source	+162.5%
Max output tokens	128,000 tokensin place when tracking began (October 7, 2026) · source	128,000 tokensin place when tracking began (October 7, 2026) · source	0%

Benchmarks

Same benchmark and source on both sides; settings named where they differ

Benchmark	gpt-5.4-nano	gpt-6-luna	Change
Arena TextArena, max effort (vs high effort). Ranges don't overlap.	1401 ±4	1443 ±5	+42
Arena Text: CodingArena, max effort (vs high effort). Ranges don't overlap.	1460 ±6	1507 ±7	+47
Arena VisionArena, max effort (vs high effort). Ranges don't overlap.	1199 ±6	1241 ±12	+42
FrontierMath Tier 4Epoch AI, max effort (vs high effort).	12.2%	56.1%	+43.9 pts
FrontierMath Tiers 1-3Epoch AI, max effort (vs high effort).	44.9%	78.9%	+34.0 pts
GPQA DiamondEpoch AI, max effort (vs high effort).	78.5%	90.5%	+12.0 pts
OTIS Mock AIME 2024-2025Epoch AI, max effort (vs high effort).	87.8%	98.9%	+11.1 pts
SimpleQA VerifiedEpoch AI, max effort (vs high effort).	11.7%	41.4%	+29.7 pts

A score from one source is never compared with another source's, and company-reported scores are compared only within the same company; settings named where they differ. Data: Arena (arena.ai), CC BY 4.0; Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

Features and parameters

Compare models

Same on both

Structured outputs: supported on both.gpt-5.4-nano: in place when tracking began (October 6, 2026) · source · gpt-6-luna: in place when tracking began (October 7, 2026) · source
Function calling: supported on both.gpt-5.4-nano: in place when tracking began (October 6, 2026) · source · gpt-6-luna: in place when tracking began (October 7, 2026) · source
Prompt caching: supported on both.gpt-5.4-nano: in place when tracking began (October 6, 2026) · source · gpt-6-luna: in place when tracking began (October 7, 2026) · source
Batch API: supported on both.gpt-5.4-nano: in place when tracking began (October 7, 2026) · source · gpt-6-luna: in place when tracking began (October 7, 2026) · source
Image input: supported on both.gpt-5.4-nano: in place when tracking began (October 7, 2026) · source · gpt-6-luna: in place when tracking began (October 7, 2026) · source
Reasoning / thinking: supported on both.gpt-5.4-nano: in place when tracking began (October 7, 2026) · source · gpt-6-luna: in place when tracking began (October 7, 2026) · source
Fine-tuning: not supported on both.gpt-5.4-nano: in place when tracking began (October 7, 2026) · source · gpt-6-luna: in place when tracking began (October 7, 2026) · source
Built-in web search: supported on both.gpt-5.4-nano: in place when tracking began (October 7, 2026) · source · gpt-6-luna: in place when tracking began (October 7, 2026) · source

Not published for gpt-5.4-nano: PDF input, temperature parameter, top_p parameter, logprobs.

Not published for gpt-6-luna: PDF input, temperature parameter, top_p parameter, logprobs.

Free tier

gpt-5.4-nano: no free tier listed

gpt-6-luna: Free for shared data, 1M tokens a day for Launch and Grow (250K for Build), in place when tracking began (October 12, 2026) (source) · All free models

gpt-6-luna adds a free tier.

Aliases

All aliases

No aliases point at either model.

On cloud platforms

All platform dates

Model	Platform	Platform ID	Shutdown	Time left
gpt-5.4-nano	Microsoft Foundryversion 2026-03-17	gpt-5.4-nano	Sep 21, 2027Active	341 days

Read daily from each platform's own pages. The status above uses each company's own date. Time left counts to 00:00 UTC on the shutdown date, which is the evening before in ET.

Checklist

Change the model string from gpt-5.4-nano to gpt-6-luna.

Time until shutdown

167days

11hours

24min

13sec

Counting to 8:00 pm ET on March 31, 2027, which is 00:00 UTC on April 1, 2027.

Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: gpt-5.4-nano, gpt-6-luna.