GPT-5.3 Chat
OpenAI · released Mar 3, 2026
- Type
- Closed
- Input
- $1.75
- Output
- $14.00
- Cached
- $0.17
List price · per 1M tokens · OpenAI at 128K context · machine-readable source ↗
Our take
Written Sep 30, 2026GPT-5.3 Chat is a hosted-only model: we list no download for it, so using it means choosing a host. Its measured quality sits mid-field, placing 50th of 168 on Arena Text (overall) as of 25 Sep 2026, a board that records which answer people preferred rather than whether it was correct.
Reach for it when you want one hosted model that takes text, images and files in the same request, or when you would rather bill through the cloud account you already have. Its placings are preference votes, not correctness measures, so treat them as a rough sense of standing rather than proof it will get your work right. Skip it if you need a model you can download and run yourself, or if you need top-of-board measured quality.
The case for it
- Text, images and files go into the same request, so a document or a screenshot does not have to be retyped or described in words first.
- All three hosts list the same rate, so the choice between them comes down to your existing billing and region rather than price.
- The request capacity holds a long report beside the question, though reliable recall across all of it is unverified in our data.
The case against it
- Mid-field on every board we hold: 50th of 168 on Arena Text (overall) and 53rd of 168 on Arena Coding as of 25 Sep 2026, consistently around the middle rather than near the top.
- All six placings come from human pairwise preference votes, which record which answer people liked, not whether it was right; no accuracy benchmark is supplied.
- We list no download for it, so a host is the only route we can point you to and the per-token bill applies to every request.
How good is it?
EverydayGeneral questions and everyday reasoning
Arena Text (overall)50th of 168 · 1450
CodingWriting and fixing code on its own
Arena Coding53rd of 168 · 1498
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing56th of 168 · 1408
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 model6 scoresEvery figure we hold, from 6 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 between 60 min and 55 days ago — each listing carries its own date.
OpenAI, direct
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 128K of context.
- per 1M tokens
- $1.75 in / $14.00 out
- Context served
- 128K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $1.75 / $14.00checked 53 days ago | 128K | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AIThrough OpenRouter | $1.75 / $14.00checked 55 days ago | 128K | not measured | No | No | Unknown |
| OpenAIDirect | $1.75 / $14.00checked 60 min ago | 128K16K max reply | not measured | No | Yesunknown period | Unknown |
OpenRouter
Microsoft Azure AIAcross the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 does not say. 0 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 |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Microsoft Azure AIThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenAIDirect | ✓ | ✓ | ✓ |
Tool calling: 3 of 3 listings say yes. JSON output: 3 of 3 listings say yes. Strict schema: 3 of 3 listings say yes.
Models people weigh against GPT-5.3 Chat
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 3 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-chat