GPT-5 Nano
OpenAI · released Aug 7, 2025
- Type
- Closed
- Input
- $0.050
- Output
- $0.40
- Cached
- $0.005
List price · per 1M tokens · OpenAI at 272K context · machine-readable source ↗
Our take
Written Sep 5, 2026GPT-5 Nano is OpenAI's smallest proprietary model, handling up to 400,000 tokens of text and images in a single request. It is priced for volume and scores highest on coding tasks, though it is the weakest of its six measured variants at creative writing.
Pick this for high-volume text and image processing where long context matters, or for coding assistance with measured software-engineering skills. Use it for long-document analysis at 400,000 tokens, or Azure enterprise deployments needing higher throughput. Skip it if creative writing is central, or if you need open weights for compliance or self-hosting.
The case for it
- Lowest published price in its own offer set, with input and output both half the cost of the next tier up.
- Fastest measured throughput in its tracked offers, nearly twice the speed of the matching Azure tier.
- Strongest measured skill is coding: 46.5 points above its own general baseline on the Arena leaderboard.
- Resolves over one-third of real GitHub issues end-to-end on SWE-bench Verified.
The case against it
- Creative writing is its weakest measured skill, 137.2 points below its own coding score.
- No price advantage at higher throughput tiers: double the cost for under 6% more speed.
- Azure's cheapest tier is slower than its own premium tier, where 10% more cost buys 60% more speed.
How good is it?
A small text model for quick everyday jobs, though it trails most models on questions, writing and code.
- getting answers to everyday questionsArena Text (overall) · 131st of 168
- drafts, rewrites and editingArena Creative Writing · 150th of 168
- writing and completing codeArena Coding · 128th of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)131st of 168 · 1338
CodingWriting and fixing code on its own
Arena Coding128th of 168 · 1384
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent. It is on SWE-bench Verified, in 33rd of 42 with 34.8.
WritingDrafting and rewriting prose
Arena Creative Writing150th of 168 · 1247
Arena Creative Writing is the only board that has scored it for this.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model7 scoresEvery figure we hold, from 7 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to rent it
Prices checked 2 hours ago — each listing carries its own date.
Microsoft Azure AI, through OpenRouter
Why this differs from the header. The strip above quotes OpenAI's own list price; this is the cheapest live offer, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $0.050 in / $0.40 out
- Context served
- 400K
- Throughput
- ~64 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenAIflex tierThrough OpenRouter | $0.025 / $0.20checked 2 hours ago | 400K128K max reply | 68 tok/s | No | Yesunknown period | Unknown |
| OpenRouterOpenRouter's own listing | $0.050 / $0.40checked 2 hours ago | 400K | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AIThrough OpenRouter | $0.050 / $0.40checked 2 hours ago | 400K360K max reply | 64 tok/s | No | No | Confirmed |
| OpenAIDirect | $0.050 / $0.40checked 2 hours ago | 272K128K max reply | 100 tok/s | No | Yesunknown period | Unknown |
| Microsoft Azure AIswedencentralThrough OpenRouter | $0.055 / $0.44checked 2 hours ago | 400K360K max reply | 96 tok/s | No | No | Confirmed |
OpenRouterAcross the 5 listings we hold: 4 say they do not train on prompts, 0 say they do and 1 does not say. 2 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenAIflexThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Microsoft Azure AIThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenAIDirect | ✓ | ✓ | ✓ |
| Microsoft Azure AIswedencentralThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 5 of 5 listings say yes. JSON output: 5 of 5 listings say yes. Strict schema: 5 of 5 listings say yes.
Models people weigh against GPT-5 Nano
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 5 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text, images and documents in, text out
- Catalogue slug
- openai-gpt-5-nano