Inference
EN
OpenAI

GPT-5.2 Pro

GPT-5.2 Pro is a reasoning model from OpenAI in the GPT-5.2 family. It has 6 scored results in 2 categories. It has no index.

  • Closed weights
  • Reasoning
  • Input: image · text · file
  • Released 2025-12
UnrankedEnough results for an index.
IndexAll categories, out of 100.UnrankedMedian 51.0
CoverageIndex weight that has results.25%
SpeedOutput tokens per second.9/sMedian 67/s
First tokenSeconds to the first output token.4.8 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$21.00batch $10.50Median $0.60
Output / 1MUS dollars per 1M output tokens.$168.00batch $84.00 Batch price per 1M output tokens.Median $2.55
ContextMaximum tokens in one request.400KMedian 262K
EloLMArena rating and rank.—Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
openai/gpt-5.2-pro
Max outputMaximum output tokens per request.
128K
Knowledge cutoffLast date of training data.
—
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
—
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
2 providers
ProviderTypeMaker, cloud, host or router.InputOutputContext
DigitalOceanCloud$21.00$168.00400K
OpenRouterRouter$21.00$168.00400K

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.None counted——
CodingCode writing and repair.None counted——
ReasoningLogic problems and puzzles.3 counted70.7—
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.None counted——
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.3 counted70.5—

Results

6 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
FrontierMath-Tier-4-2025-07-01-PrivateMath31.3% ±6.75 / 55
Chess PuzzlesReasoning60.0% ±4.99 / 90
ARC-AGI-1 (semi-private)Reasoning90.5%35 / 126
FrontierMath-Tiers-1-3-v2-PrivateMath74.0% ±2.625 / 90
ARC-AGI-2 (semi-private)Reasoning54.2%47 / 131
FrontierMath-Tier-4-v2-PrivateMath46.0% ±7.827 / 72
ARC-AGI-1 (public eval)Reasoning97.6%17 / 116
ARC-AGI-2 (public eval)Reasoning51.7%45 / 122

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseARC Prize FoundationTerms restrict reuseEpoch AICC BYmodels.devMIT

History

5 releases
Output / 1M$168.00 → $168.00
23 Oct 202612 Nov 2026

Questions

How much does GPT-5.2 Pro cost?
$21.00 per 1M input tokens, $168.00 per 1M output tokens.
How fast is GPT-5.2 Pro?
9 output tokens per second, 4.8 s to the first token.
What is the context window of GPT-5.2 Pro?
400K tokens.
Is GPT-5.2 Pro open source?
No. Its weights are not published.
When was GPT-5.2 Pro released?
December 2025.

More from OpenAI

All models
GPT-5.259.0GPT-5.2 InstantUnrankedGPT-5.2 ChatUnrankedGPT-5.2-Codex59.9GPT-5.1-Codex-Max53.8