Migrating from gpt-5.1 to gpt-5.2

What changes when you move from gpt-5.1 to gpt-5.2: input price +40%, output price +40%.

From: gpt-5.1
Status: Deprecated
Shutdown: Apr 1, 2027
Time left: 168 days

To: gpt-5.2
Status: Active
Shutdown: none announced
Time left: —

Prices

USD per 1M tokens, standard tier

Type	gpt-5.1	gpt-5.2	Change
Input	$1.25first seen October 1, 2026 · source	$1.75first seen October 1, 2026 · source	+40%
Cached input	$0.125first seen October 1, 2026 · source	$0.175first seen October 1, 2026 · source	+40%
Output	$10.00first seen October 1, 2026 · source	$14.00first seen October 1, 2026 · source	+40%

At 1M input and 250K output tokens a month: $3.75 on gpt-5.1, $5.25 on gpt-5.2 (+40%).

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

Limits

Tokens

Limit	gpt-5.1	gpt-5.2	Change
Context window	400,000 tokensin place when tracking began (October 6, 2026) · source	400,000 tokensin place when tracking began (October 6, 2026) · source	0%
Max output tokens	128,000 tokensin place when tracking began (October 6, 2026) · source	128,000 tokensin place when tracking began (October 6, 2026) · source	0%

Benchmarks

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

Benchmark	gpt-5.1	gpt-5.2	Change
Arena TextArena, high effort. Ranges don't overlap. Other settings 1439 ±4 → 1435 ±3	1456 ±4	1437 ±4	−19
Arena Text: CodingArena, high effort. Other settings 1476 ±7 → 1482 ±5	1492 ±7	1489 ±6	−3 within range
Arena WebDevArena. Ranges don't overlap.	1341 ±8	1417 ±23	+76
Arena VisionArena, high effort. Other settings 1240 ±8 → 1229 ±6	1251 ±8	1243 ±6	−8 within range
Arena SearchArena. Ranges don't overlap. Other settings not rated → 1136 ±6 no reasoning	1184 ±5	1161 ±6	−23
Arena DocumentArena. Other settings not rated → 1423 ±9 high effort	1416 ±9	1425 ±6	+9 within range
GPQA DiamondEpoch AI, xhigh effort (vs high effort). Other settings 87.6% → 88.2% high effort 85.0% → 87.9% medium effort not run → 82.7% low effort 66.7% → 73.2% no reasoning	87.6%	91.4%	+3.8 pts
OTIS Mock AIME 2024-2025Epoch AI, xhigh effort (vs high effort). Other settings 88.6% → 96.1% high effort 85.6% → 93.9% medium effort 63.9% → 78.9% low effort 37.8% → 62.2% no reasoning	88.6%	96.1%	+7.5 pts
SimpleQA VerifiedEpoch AI, xhigh effort (vs high effort). Other settings 48.0% → 34.3% high effort not run → 32.8% low effort not run → 32.7% medium effort	48.0%	37.1%	−10.9 pts
SWE-bench VerifiedEpoch AI, high effort.	68.0%	73.8%	+5.8 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-5.1: in place when tracking began (October 6, 2026) · source · gpt-5.2: in place when tracking began (October 6, 2026) · source
Function calling: supported on both.gpt-5.1: in place when tracking began (October 6, 2026) · source · gpt-5.2: in place when tracking began (October 6, 2026) · source
Prompt caching: supported on both.gpt-5.1: in place when tracking began (October 6, 2026) · source · gpt-5.2: in place when tracking began (October 6, 2026) · source
Batch API: supported on both.gpt-5.1: in place when tracking began (October 6, 2026) · source · gpt-5.2: in place when tracking began (October 6, 2026) · source
Image input: supported on both.gpt-5.1: in place when tracking began (October 6, 2026) · source · gpt-5.2: in place when tracking began (October 6, 2026) · source
Reasoning / thinking: supported on both.gpt-5.1: in place when tracking began (October 6, 2026) · source · gpt-5.2: in place when tracking began (October 6, 2026) · source
Fine-tuning: not supported on both.gpt-5.1: in place when tracking began (October 6, 2026) · source · gpt-5.2: in place when tracking began (October 6, 2026) · source
Built-in web search: supported on both.gpt-5.1: in place when tracking began (October 6, 2026) · source · gpt-5.2: in place when tracking began (October 6, 2026) · source

Not published for gpt-5.1: PDF input, temperature parameter, top_p parameter, logprobs.

Not published for gpt-5.2: PDF input, temperature parameter, top_p parameter, logprobs.

Aliases

All aliases

No aliases point at either model.

On cloud platforms

All platform dates

Model	Platform	Platform ID	Shutdown	Time left
gpt-5.1	Microsoft Foundryversion 2025-11-13	gpt-5.1	May 15, 2027Active	212 days
gpt-5.2	Microsoft Foundryversion 2025-12-11	gpt-5.2	Jun 8, 2027Active	236 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-5.1 to gpt-5.2.
Re-check costs: gpt-5.2 costs more than gpt-5.1 (input +40%, output +40%).

Time until shutdown

167days

11hours

08min

08sec

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-5.1, gpt-5.2.