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

GPT-5 Nano

API ID gpt-5-nano

gpt-5-nano is an OpenAI model, released August 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 $0.05 input and from $0.40 output per 1M tokens.

Status
Active
Released
August 2025
Shutdown
none announced
Replacement
—

No deprecation or shutdown date has been announced as of October 15, 2026.

Benchmarks

Scores as each source published them
or

Comparing with GPT-4.1 nano, 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 NanoGPT-4.1 nanoChangeRankDateSource
Text
By category
  • Math 1346 rank 218 vs 1273 (+73) at high effort (vs no setting)
  • Creative writing 1247 rank 296 vs 1307 (−60) at high effort (vs no setting)
  • Instruction following 1327 rank 228 vs 1300 (+27) at high effort (vs no setting)
  • Hard prompts 1356 rank 230 vs 1333 (+23, within range) at high effort (vs no setting)
  • Long prompts 1332 rank 248 vs 1325 (+7, within range) at high effort (vs no setting)
  • Multi-turn 1325 rank 242 vs 1314 (+11, within range) at high effort (vs no setting)
  • Expert 1355 rank 217 vs 1313 (+42, within range) at high effort (vs no setting)
1338 ±71322 ±8+16235 of 415
8,132 votes		Oct 13, 2026source
Text: Coding1385 ±151373 ±19+12
within range		230 of 410
1,665 votes		Oct 13, 2026source
Vision1146 ±111089 ±18+57118 of 165
3,929 votes		Oct 9, 2026source

Rated as gpt-5-nano-high (high effort); GPT-4.1 nano as gpt-4.1-nano-2025-04-14. Some were rated at different settings; ratings on one arena share one scale, so the difference still reads directly. Ratings come from people voting between two anonymous answers; Text and Vision are style-controlled, as on arena.ai. Data: Arena (arena.ai), CC BY 4.0.

Alias

All aliases

Currently points to gpt-5-nano-2025-08-07 (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
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, Built-in web search, temperature parameter, top_p parameter, logprobs.

Price history

USD per 1M tokens, standard tier
$0.00$0.10$0.20$0.30$0.40$0.50Oct 2026In $0.05Out $0.40Oct 1, 2026 to Oct 15, 2026: Input $0.05, Output $0.40
$0.00$0.10$0.20$0.30$0.40$0.50Oct 2026In $0.05Out $0.40Oct 1, 2026 to Oct 15, 2026: Input $0.05, Output $0.40

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$0.05
Oct 1, 2026Output$0.40

Prices

USD per 1M tokens, every type and band, by tier
TypeBandPrice $/1MIn effect
Standard
inputshort context$0.05
cached inputshort context$0.005
outputshort context$0.40
Batch
inputshort context$0.025
cached inputshort context$0.0025
outputshort context$0.20
Flex
inputshort context$0.025
cached inputshort context$0.0025
outputshort context$0.20

Changelog

Changes we detected on OpenAI's pages

No changes recorded yet.

Email alerts

Get an email if gpt-5-nano changes

We'll email you the same morning we spot a deprecation notice, a new or moved shutdown date, a price change, or the model leaving OpenAI's model list.

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

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