All times Eastern (ET)Provider pages checked daily at
ProSign inRSS

GPT-5.1

API ID gpt-5.1

gpt-5.1 is an OpenAI model, released November 2025. It has a 400,000-token context window and up to 128,000 output tokens. It takes image input and supports function calling, structured outputs and reasoning. Standard price: from $1.25 input and from $10.00 output per 1M tokens.

Status
Deprecated
Released
November 2025
Shutdown
Apr 1, 2027

It stops serving on April 1, 2027. Recommended replacement: gpt-6-sol.

How to migrate to GPT-6 Sol

Benchmarks

Scores as each source published them
or

Comparing with GPT-5, the previous model in this line. A score is compared only with the same benchmark from the same source, at the same setting where both have it. Full comparison: prices, limits, features

Arena

ArenaGPT-5.1GPT-5ChangeRankDateSource
Text
Other settings
  • 1439 ±4 vs not rated
By category
  • Math 1458 rank 66 vs 1435 (+23, within range)
  • Creative writing 1428 rank 75 vs 1373 (+55)
  • Instruction following 1450 rank 65 vs 1410 (+40)
  • Hard prompts 1476 rank 71 vs 1448 (+28)
  • Long prompts 1460 rank 75 vs 1413 (+47)
  • Multi-turn 1464 rank 73 vs 1421 (+43)
  • Expert 1481 rank 70 vs 1459 (+22, within range)
1456 ±41435 ±5+2169 of 415
41,669 votes		Oct 13, 2026source
Text: Coding
Other settings
  • 1476 ±7 vs not rated
1492 ±71471 ±8+2192 of 410
8,421 votes		Oct 13, 2026source
WebDev
Other settings
  • 1341 ±8 vs not rated
1395 ±121417 ±16−22
within range		94 of 142
4,911 votes		Oct 13, 2026source
Vision
Other settings
  • 1240 ±8 vs not rated
1251 ±81210 ±7+4152 of 165
9,861 votes		Oct 9, 2026source
Search1184 ±51188 ±7−4
within range		30 of 42
63,042 votes		Oct 13, 2026source
Document1416 ±9not rated43 of 44
8,244 votes		Sep 13, 2026source

Rated as gpt-5.1-high (high effort); GPT-5 as gpt-5-high (high effort). Ratings come from people voting between two anonymous answers; Text, Vision, Search and Document are style-controlled, as on arena.ai. Data: Arena (arena.ai), CC BY 4.0.

Epoch AI

BenchmarkGPT-5.1GPT-5ChangeSettingRunSource
GPQA Diamond
Other settings
  • 85.0% vs not run medium effort
  • 66.7% vs not run no reasoning
87.6%not runhigh effortNov 13, 2025source
OTIS Mock AIME 2024-2025
Other settings
  • 85.6% vs not run medium effort
  • 63.9% vs not run low effort
  • 37.8% vs not run no reasoning
88.6%not runhigh effortNov 13, 2025source
SimpleQA Verified48.0%not runhigh effortAug 27, 2026source
SWE-bench Verified68.0%not runhigh effortFeb 18, 2026source

Run independently by Epoch AI. Data: Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

On cloud platforms

All platform dates
PlatformPlatform IDStateShutdownTime leftReplacementSource
Microsoft Foundryversion 2025-11-13gpt-5.1ActiveMay 15, 2027212 days—source

Microsoft Foundry (version 2025-11-13) retires this model 44 days after OpenAI's own API.

Read daily from each platform's own pages. The shutdown date and countdown on this page use OpenAI's own date. Time left counts to 00:00 UTC on the shutdown date, which is the evening before in ET.

Alias

All aliases

Currently points to gpt-5.1-2025-11-13 (in place when tracking began (October 7, 2026)).

Features

Compare models
FeatureValueSinceSource
Structured outputsThe model can be held to a JSON schema you supply, so every reply parses without retries or cleanup.Supportedin place when tracking began (October 6, 2026)source
Function callingAlso called tool use. You describe functions; the model replies with a function name and arguments for your code to run, then uses the result.Supportedin place when tracking began (October 6, 2026)source
Prompt cachingA prompt prefix you send again and again (system prompt, documents, tools) is cached, so later requests cost less and start faster.Supportedin place when tracking began (October 6, 2026)source
Batch APISend many requests as one job that runs in the background, usually finished within 24 hours, at a lower price than live requests.Supportedin place when tracking began (October 6, 2026)source
Image inputImages such as screenshots, photos and charts can go in the prompt for the model to read.Supportedin place when tracking began (October 6, 2026)source
Reasoning / thinkingThe model can work through a problem step by step before it answers: usually better answers to hard questions, at the cost of more tokens and time.Supportedin place when tracking began (October 6, 2026)source
Fine-tuningYou can train your own version of the model on your examples through the company's API, then call it like any other model.Not supportedin place when tracking began (October 6, 2026)source
Built-in web searchThe company's API can search the web for the model during a request and cite its sources; you don't need a search service of your own.Supportedin place when tracking began (October 6, 2026)source
Context windowThe most the model can work with in one request, in tokens: your prompt, conversation history and files. A token is about three-quarters of an English word.400,000 tokensin place when tracking began (October 6, 2026)source
Max output tokensThe longest reply the model can write in one response, in tokens. A token is about three-quarters of an English word.128,000 tokensin place when tracking began (October 6, 2026)source

Not published by OpenAI: PDF input, temperature parameter, top_p parameter, logprobs.

Price history

USD per 1M tokens, standard tier
$0.00$2.50$5.00$7.50$10.00$12.50Oct 2026In $1.25Out $10.00Oct 1, 2026 to Oct 15, 2026: Input $1.25, Output $10.00
$0.00$2.50$5.00$7.50$10.00$12.50Oct 2026In $1.25Out $10.00Oct 1, 2026 to Oct 15, 2026: Input $1.25, Output $10.00

We started recording this model's prices on Oct 1, 2026. The history grows with each daily check.

Show as a table
FromTypePrice
Oct 1, 2026Input$1.25
Oct 1, 2026Output$10.00

Prices

USD per 1M tokens, every type and band, by tier
TypeBandPrice $/1MIn effect
Standard
inputshort context$1.25
cached inputshort context$0.125
outputshort context$10.00
Batch
inputshort context$0.625
cached inputshort context$0.0625
outputshort context$5.00
Flex
inputshort context$0.625
cached inputshort context$0.0625
outputshort context$5.00
Fast
inputshort context$2.50
cached inputshort context$0.25
outputshort context$20.00

Changelog

Changes we detected on OpenAI's pages
  1. Deprecated

    OpenAI deprecated gpt-5.1: shuts down Apr 1, 2027

    Breaking

Related news

Time until shutdown
167days
11hours
26min
23sec

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

Email alerts

Get an email before gpt-5.1 shuts down

We'll email you 30, 7 and 1 days before it shuts down, and the same morning if the shutdown date moves or the price changes.

No password: one email to confirm, and you can unsubscribe any time. Privacy

Last checked · Sources: OpenAI deprecations, OpenAI pricing, OpenAI models