← Models

GPT-5.2

OpenAI · GPT-5

Previous GPT-5.2 frontier route now mainly useful for compatibility after GPT-5.5 became OpenAI's recommended fresh-build model.

Part of GPT family · Other versions: GPT-5.6 Luna , GPT-5.6 Terra , GPT-5.6 Sol , GPT-5.5 Pro , GPT-5.5 , GPT-Rosalind , GPT-5.4 mini , GPT-5.4 nano , GPT-5.4 Pro , GPT-5.4 , GPT-5.3 , GPT-5.3-Codex , GPT-5.2-Codex , GPT-5.2 Pro , GPT-5-Codex , GPT-5 mini , GPT-5 nano , GPT-5 , GPT-4.1 , GPT-4o mini Transcribe , GPT-4o mini TTS , GPT-4o Transcribe , Computer Use Preview , GPT-4o mini , GPT-4o
Type
language
Context
400K tokens
Max Output
128K tokens
Status
legacy
Input
$1.75/1M tok
Output
$14/1M tok
API Access
Yes
License
proprietary
reasoning coding agentic tool-use long-context instruction-following
Released December 2025 · Updated June 8, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on June 8, 2026.

GPT-5.2 is an older GPT-5 frontier route in OpenAI’s API catalog. It remains useful for existing integrations and compatibility testing, but it should no longer be described as the default recommendation for new OpenAI builds. OpenAI’s current latest-model guidance points new coding, reasoning, and agentic workloads toward GPT-5.5 first, with GPT-5.4 also sitting above GPT-5.2 in the newer frontier stack.

Capabilities

GPT-5.2 is strongest on multi-step reasoning, technical writing, code generation, image-aware work, and structured task execution where strong instruction compliance matters. For teams already tuned around its behavior, it can still be a practical route for stable production workloads while newer GPT-5.4 / GPT-5.5 routes are evaluated.

Technical Details

OpenAI’s current model card lists GPT-5.2 with a 400K context window, 128K max output, image input support, and configurable reasoning effort. It supports modern tool-use and orchestration patterns in the API stack, which keeps it viable for long-context assistants and agent workflows that already depend on this branch.

Pricing & Access

Published API pricing (per 1M tokens):

  • Input: $1.75
  • Cached input: $0.175
  • Output: $14.00

Access remains available through OpenAI API model endpoints. New systems should compare it against GPT-5.5 and GPT-5.4 before adopting it as a default.

Best Use Cases

Use GPT-5.2 for compatibility-sensitive production assistants, coding agents, document workflows, and general professional applications that already target this route. For greenfield systems, treat it as a baseline in migration tests rather than the default answer.

Comparisons

  • GPT-5.5 (OpenAI): Newer recommended route for fresh complex coding, reasoning, and agentic builds.
  • GPT-5.4 (OpenAI): Newer frontier option with broader current positioning than GPT-5.2.
  • GPT-5.3-Codex (OpenAI): Better choice when the workload is explicitly long-horizon software engineering.
  • Claude Sonnet 4.6 (Anthropic): Contemporary alternative for broad production use.