GPT-5.2 Chat
OpenAI · released Dec 10, 2025
- 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 2, 2026GPT-5.2 Chat is OpenAI's flagship text model that accepts images and files alongside text, with a 128,000-token request limit. It offers a wide speed-for-cost trade-off across six tiers, and scores among the strongest on measured mathematics performance.
Pick this for mathematical reasoning at measured top-tier levels, or for general coding and reasoning when the cheapest tier fits your budget. Use it for enterprise deployments needing 128K context with governance compliance. Skip it if you need agentic coding — its score there lags far behind its standard coding result — or if the premium tiers stretch your budget, since the top tier costs several times the entry one.
The case for it
- LiveBench Mathematics 93.17%, among the strongest measured scores on that board.
- LiveBench Reasoning 83.21% and Coding 76.07% in automated evaluation.
- Arena Coding 1514.84, above its own overall text score.
- Six tiers from the same model let you trade speed for cost.
The case against it
- Agentic coding lags 25.82 points behind its own standard coding score.
- Instruction following is its lowest LiveBench subscore except agentic coding, at 61.77%.
- Web development scores 98.4 points below its general coding appeal.
How good is it?
A general chat model for everyday questions, drafting and coding, with no measured weak spots on this board.
- getting answers to everyday questionsArena Text (overall) · 22nd of 168
- drafts, rewrites and editingArena Creative Writing · 42nd of 168
- writing and completing codeArena Coding · 30th of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)22nd of 168 · 1476
Also on this board: 1437 (Sep 25, 2026). Read the pair, not the higher one.
CodingWriting and fixing code on its own
Arena Coding30th of 168 · 1515
Also on this board: 1489 (Sep 25, 2026). Read the pair, not the higher one.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent. It is on LiveBench Agentic Coding, in 36th of 58 with 50.25.
WritingDrafting and rewriting prose
Arena Creative Writing42nd of 168 · 1433
Also on this board: 1387 (Sep 25, 2026). Read the pair, not the higher one.
Boards this model appears on that none of the ratings above are built on.
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.
Where to rent it
Prices checked 4 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
- $1.75 in / $14.00 out
- Context served
- 400K
- Throughput
- ~38 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenAIflex tierThrough OpenRouter | $0.88 / $7.00checked 4 hours ago | 400K128K max reply | 48 tok/s | No | Yesunknown period | Unknown |
| 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 | 38 tok/s | No | No | Confirmed |
| OpenAIDirect | $1.75 / $14.00checked 4 hours ago | 128K16K max reply | 46 tok/s | No | Yesunknown period | Unknown |
| OpenAIfast tierThrough OpenRouter | $3.50 / $28.00checked 4 hours ago | 400K128K max reply | 95 tok/s | No | Yesunknown period | Unknown |
OpenRouterAcross the 5 listings we hold: 4 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 |
|---|---|---|---|
| OpenAIflexThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Microsoft Azure AIThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenAIDirect | ✓ | ✓ | ✓ |
| OpenAIfastThrough 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-5.2 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 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-5-2-chat