GPT-5.2 Chat
OpenAI · released Dec 10, 2025
- Type
- Proprietary
- Input
- $1.75
- Output
- $14.00
- Cached
- $0.17
List price · per 1M tokens · OpenAI at 128K context · source ↗
Our take
Written Aug 3, 2026GPT-5.2 Chat is OpenAI's flagship hosted model that handles text, images and files in a single request. It offers a wide speed range across its tiers, with its strongest measured results on coding tasks and its weakest on creative writing.
Choose this when maximum coding performance is the priority, or when you need guaranteed OpenAI-native hosting. Pick the faster tiers if throughput is critical — the fastest option runs nearly eight times quicker than the entry one. Skip it if you need strong creative writing scores, if you want downloadable weights, or if you are looking for a cheap fast option — speed and cost are tightly coupled here.
The case for it
- Highest measured coding score in this model's data, at 1515.2 on the Arena Coding benchmark.
- Wide throughput range lets you trade cost for speed, from 11 to 86 tokens per second across tiers.
- Consistent top-quartile positioning across multiple evaluation runs on the same leaderboard date.
The case against it
- Creative writing is a relative soft spot, with its lowest benchmark score over 100 points below its coding peak.
- Entry tier is premium-priced even at its cheapest, with no sub-dollar output option available.
- Throughput and cost are tightly coupled: the fastest tier costs four times the entry tier's input and output rates, with no cheap fast option.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)12th of 143 · 1476.1
Also on this board: 1437.5 via High (Aug 2, 2026). Read the pair, not the higher one.
CodingWriting and fixing code on its own
Arena Coding18th of 143 · 1515.2
Also on this board: 1489.2 via High (Aug 2, 2026). Read the pair, not the higher one.
AgenticPlanning, calling tools, staying on task
GPT-5.2 Chat is not on Arena Agent (IPS), which is where the rating would come from, so there is no rating here. It is on SWE-bench Verified, in 7th of 39 with 72.8.
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where GPT-5.2 Chat placed and give it no mark out of five.
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, which is why they get no rating.
Every published score for this model16 scoresEvery figure we hold, from 16 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Or rent it from someone else
Why this differs from the header. The strip above quotes OpenAI's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $1.75 in / $14.00 out
- Context served
- 400K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenAIflex tier | $0.88 / $7.00 | 400K | 11 tok/s | No | Yesunknown period | Unknown |
| OpenRouter | $1.75 / $14.00 | 400K | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AI | $1.75 / $14.00 | 400K | 36 tok/s | No | No | Confirmed |
| OpenAI | $1.75 / $14.00 | 128K16K out | 39 tok/s | No | Yesunknown period | Unknown |
| OpenAIpriority tier | $3.50 / $28.00 | 400K | 86 tok/s | No | Yesunknown period | Unknown |
Microsoft Azure AIAcross the 5 listings we hold: 4 say they do not train on prompts, 0 say they do and 1 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenAIflex | ✓ | ✓ | ✓ |
| OpenRouter | ✓ | ✓ | ✓ |
| Microsoft Azure AI | ✓ | ✓ | ✓ |
| OpenAI | ✓ | ✓ | ✓ |
| OpenAIpriority | ✓ | ✓ | ✓ |
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-5.2 Chat
When we formed this view
Dates behind this page
Prices last checked 8d ago
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 do not say whether they train on prompts.
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
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text+image+file->text
- Catalogue slug
- openai-gpt-5-2-chat