GPT-5.4
OpenAI · released Mar 5, 2026
- Type
- Closed
- Input
- $2.50
- Output
- $15.00
- Cached
- $0.25
List price · per 1M tokens · OpenAI at 1.1M context · machine-readable source ↗
Our take
Written Sep 2, 2026GPT-5.4 is OpenAI's flagship text model that can handle up to 1.05 million tokens in a single request, accepting text, images and files. It scores near the top on mathematics benchmarks and offers a wide spread of provider choices, though its agentic abilities lag far behind its standard coding performance.
Pick this for long-document work at over one million tokens, mathematics-heavy tasks where it scores 94.15%, or budget batch work through the cheapest tier. Choose the fastest provider for high-throughput needs at 151 tokens per second. Skip it if you need strong agentic coding, autonomous tool use, or the ability to run weights locally.
The case for it
- Extremely large request limit of 1.05 million tokens for long-document and multimodal inputs.
- Top-tier mathematics performance at 94.15% on refreshed LiveBench tests.
- Wide provider choice with a fourfold price spread for flexibility.
- Highest measured throughput at 151 tokens per second on one provider.
The case against it
- Agentic coding lags 23.7 points behind its standard coding score.
- Arena agent scores are uniformly low across all sub-measures, near floor.
- Proprietary weights with no disclosed licence; you cannot self-host.
How good is it?
A general-purpose assistant for everyday questions, drafting and editing, coding, and calling tools to carry out requests.
- answering everyday questionsArena Text (overall) · 35th of 168
- drafting, rewriting and editing textArena Creative Writing · 41st of 168
- writing and completing codeArena Coding · 38th of 168
- calling tools to carry out requestsArena Agent · Tool use · 9th of 55
EverydayGeneral questions and everyday reasoning
Arena Text (overall)35th of 168 · 1465
Also on this board: 1475 (Sep 25, 2026). Read the pair, not the higher one.
CodingWriting and fixing code on its own
Arena Coding38th of 168 · 1511
Also on this board: 1521 (Sep 25, 2026). Read the pair, not the higher one.
AgenticPlanning, calling tools, staying on task
Arena Agent26th of 55 · 0.004
WritingDrafting and rewriting prose
Arena Creative Writing41st of 168 · 1434
Also on this board: 1443 (Sep 25, 2026). Read the pair, not the higher one.
Placings on Arena's agent boards, from live sessions people ran themselves. A model can lead on one of these and sit mid-field on the others.
Boards this model appears on that none of the ratings above are built on.
Every published score for this model20 scoresEvery figure we hold, from 20 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 4 hours ago — each listing carries its own date.
OpenAI, direct
The lab is the cheapest at this context. The strip above and this offer are the same one, compared at 1.1M of context. One cheaper row below is outside that comparison: a non-standard pricing tier.
- per 1M tokens
- $2.50 in / $15.00 out
- Context served
- 1.1M
- Throughput
- ~35 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenAIflex tierThrough OpenRouter | $1.25 / $7.50checked 4 hours ago | 1.1M128K max reply | 3 tok/s | No | Yesunknown period | Unknown |
| Microsoft Azure AIThrough OpenRouter | $2.50 / $15.00checked 4 hours ago | 1.1M128K max reply | 52 tok/s | No | No | Confirmed |
| OpenRouterOpenRouter's own listing | $2.50 / $15.00checked 4 hours ago | 1.1M | not measured | Unknown | Unknown | Unknown |
| OpenAIDirect | $2.50 / $15.00checked 4 hours ago | 1.1M128K max reply | 35 tok/s | No | Yesunknown period | Unknown |
| Microsoft Azure AIeuThrough OpenRouter | $2.75 / $16.50checked 4 hours ago | 1.1M128K max reply | 18 tok/s | No | No | Confirmed |
| Amazon Bedrockus-east-1Through OpenRouter | $2.75 / $16.50checked 4 hours ago | 1.1M128K max reply | 15 tok/s | No | No | Unknown |
| Microsoft Azure AIusThrough OpenRouter | $2.75 / $16.50checked 4 hours ago | 1.1M128K max reply | 22 tok/s | No | No | Confirmed |
| OpenAIfast tierThrough OpenRouter | $5.00 / $30.00checked 4 hours ago | 1.1M128K max reply | 52 tok/s | No | Yesunknown period | Unknown |
Microsoft Azure AI
OpenRouter
Amazon BedrockAcross the 8 listings we hold: 7 say they do not train on prompts, 0 say they do and 1 does not say. 3 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 | ✓ | ✓ | ✓ |
| Microsoft Azure AIThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| OpenAIDirect | ✓ | ✓ | ✓ |
| Microsoft Azure AIeuThrough OpenRouter | ✓ | ✓ | ✓ |
| Amazon Bedrockus-east-1Through OpenRouter | ✓ | ✓ | ✓ |
| Microsoft Azure AIusThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenAIfastThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 8 of 8 listings say yes. JSON output: 8 of 8 listings say yes. Strict schema: 8 of 8 listings say yes.
Models people weigh against GPT-5.4
When we formed this view
Recent changes
Each 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 8 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-5-4