GPT-5.3-Codex
OpenAI · released Feb 24, 2026
- Type
- Closed
- Input
- $1.75
- Output
- $14.00
- Cached
- $0.17
List price · per 1M tokens · OpenAI at 400K context · source ↗
Our take
Written Sep 2, 2026GPT-5.3-Codex is a proprietary coding specialist from OpenAI that can handle up to 400,000 tokens in a single request and accepts text, images and files. It scores well on human-rated web development tasks, though its benchmark coverage is narrow for a model pitched at coders.
Pick this when human-rated web development quality matters and you need a very large context window for codebases. Choose the standard tier for 69 tokens per second, or premium tiers for up to 87 if the extra speed justifies paying twice as much. Skip it if you need measured performance on general coding or reasoning, or if you want the fastest throughput at the standard price — Azure is less than half the speed for the same rate.
The case for it
- Strong human-rated performance on web-app building tasks, with an Arena Code score of 1408.3 from human votes.
- 400,000-token request limit, very large for codebases and documentation.
- Throughput scales with tier on OpenAI direct: up to 87 tokens per second at the premium tier.
The case against it
- Double the output cost for premium tiers brings only 10–26% more throughput.
- Only one benchmark measured: no general coding, reasoning or chat scores disclosed.
- Azure throughput is less than half that of OpenAI at the same price tier.
How good is it?
EverydayGeneral questions and everyday reasoning
Not yet scored on Arena Text (overall).
CodingWriting and fixing code on its own
Not yet scored on Arena Coding. It is on Arena Code (WebDev), in 57th of 95 with 1408.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Not yet scored on Arena Creative Writing.
Every published score for this model1 scoreEvery figure we hold, from 1 board, 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, through OpenRouter
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts OpenAI on 400K of context.
- per 1M tokens
- $1.75 in / $14.00 out
- Context served
- 400K
- Throughput
- ~62 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $1.75 / $14.00checked 4 hours ago | 400K | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AIThrough OpenRouter | $1.75 / $14.00checked 4 hours ago | 400K128K max reply | 35 tok/s | No | No | Confirmed |
| OpenAIThrough OpenRouter | $1.75 / $14.00checked 4 hours ago | 400K128K max reply | 62 tok/s | No | Yesunknown period | Unknown |
| OpenAIfast tierThrough OpenRouter | $3.50 / $28.00checked 4 hours ago | 400K128K max reply | 8 tok/s | No | Yesunknown period | Unknown |
OpenRouter
Microsoft Azure AIAcross the 4 listings we hold: 3 say they do not train on prompts, 0 say they do and 1 does not say. 1 appears 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 |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Microsoft Azure AIThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenAIThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenAIfastThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 4 of 4 listings say yes. JSON output: 4 of 4 listings say yes. Strict schema: 4 of 4 listings say yes.
Models people weigh against GPT-5.3-Codex
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 4 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-5-3-codex