Migrating from gpt-5-nano-2025-08-07 to gpt-5.6-luna

What changes when you move from gpt-5-nano-2025-08-07 to gpt-5.6-luna: prices, limits, features and parameters, read from each company's own pages.

From: gpt-5-nano-2025-08-07
Status: Deprecated
Shutdown: Dec 11, 2026
Time left: 57 days

To: gpt-5.6-luna
Status: Active
Shutdown: none announced
Time left: —

Prices

USD per 1M tokens, standard tier

Type	gpt-5-nano-2025-08-07	gpt-5.6-luna	Change
Input	Not published	$0.20first seen October 1, 2026 · source	—
Cached input	Not published	$0.02first seen October 1, 2026 · source	—
Output	Not published	$1.20first seen October 1, 2026 · source	—

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

Limits

Tokens

Limit	gpt-5-nano-2025-08-07	gpt-5.6-luna	Change
Context window	Not published	1,050,000 tokensin place when tracking began (October 7, 2026) · source	—
Max output tokens	Not published	128,000 tokensin place when tracking began (October 7, 2026) · source	—

Benchmarks

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

Benchmark	gpt-5-nano-2025-08-07	gpt-5.6-luna	Change
FrontierMath Tier 4Epoch AI, max effort (vs high effort).	2.4%	61.0%	+58.6 pts
FrontierMath Tiers 1-3Epoch AI, max effort (vs high effort). Other settings 6.0% → 41.4% low effort not run → 39.6% no reasoning	20.0%	82.1%	+62.1 pts
GPQA DiamondEpoch AI, max effort (vs high effort). Other settings 57.6% → 82.3% low effort not run → 63.6% no reasoning	69.4%	91.6%	+22.2 pts
OTIS Mock AIME 2024-2025Epoch AI, max effort (vs high effort). Other settings 46.7% → 66.7% low effort not run → 40.0% no reasoning	81.1%	98.3%	+17.2 pts
SimpleQA VerifiedEpoch AI, max effort (vs high effort).	11.7%	41.0%	+29.3 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: Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

Features and parameters

Compare models

No feature is published for both models, so none can be compared.

Not published for gpt-5-nano-2025-08-07: Structured outputs, Function calling, Prompt caching, Batch API, Image input, PDF input, Reasoning / thinking, Fine-tuning, Built-in web search, temperature parameter, top_p parameter, logprobs, Context window, Max output tokens.

Not published for gpt-5.6-luna: PDF input, temperature parameter, top_p parameter, logprobs.

Free tier

gpt-5-nano-2025-08-07: Free for shared data, 10M tokens a day for Launch and Grow (2.5M for Build), in place when tracking began (October 12, 2026) (source)

gpt-5.6-luna: Free for shared data, 10M tokens a day for Launch and Grow (2.5M for Build), in place when tracking began (October 12, 2026) (source) · All free models

Aliases

All aliases

Aliases pointing at gpt-5-nano-2025-08-07: gpt-5-nano (in place when tracking began (October 7, 2026) · source)

No aliases point at gpt-5.6-luna.

On cloud platforms

All platform dates

Model	Platform	Platform ID	Shutdown	Time left
gpt-5-nano-2025-08-07	Microsoft Foundryversion 2025-08-07	gpt-5-nano	Feb 9, 2027Active	117 days
gpt-5.6-luna	Amazon Bedrock	openai.gpt-5.6-luna	not before Jul 13, 2027Active
gpt-5.6-luna	Microsoft Foundryversion 2026-07-09	gpt-5.6-luna	Jan 11, 2028Active	453 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-nano-2025-08-07 to gpt-5.6-luna.

Time until shutdown

56days

11hours

23min

52sec

Counting to 7:00 pm ET on December 10, 2026, which is 00:00 UTC on December 11, 2026.

Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: gpt-5-nano-2025-08-07, gpt-5.6-luna.