Models/OpenAI/GPT-5.2-Codex

GPT-5.2-Codex

DEPRECATED
OpenAI · Proprietary · Released Jan 14, 2026 · openai/gpt-5.2-codex
Best $1.75 in / $14.00 out via Azure
CompareEstimate cost
400K contextVisionToolsReasoningStructured outputPrompt caching
Available from 3 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 24 HOURS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
PROVIDERINPUTOUTPUTCACHECONTEXTQUANTTTFTTPSUPTIME
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · methodology v1.1 · measured 24 hours ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$1.75 / $14.00
per MTok in / out
CACHE READ $0.175WEB SEARCH $0.01 / search
Recent changesRSS ↗
Sep 23, 2026endpoint added · cheaperinference1 → 3
About

GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

Specifications
Context window400,000
Max output128,000
Modalities intext, image
Modalities outtext
LicenseProprietary
ReleasedJan 14, 2026
TokenizerGPT
Deprecation2026-07-23
Embed badge
GPT-5.2-Codex price and speed badge
[![GPT-5.2-Codex](https://modelindex.ai/badge/openai/gpt-5.2-codex)](https://modelindex.ai/models/openai/gpt-5.2-codex)
Sources
OpenRouter API23 minutes ago
AGGREGATOR
LiteLLM dataset23 minutes ago
AGGREGATOR
ModelIndex benchmarks16 days ago
MEASURED
Verified 23 minutes ago · list prices, not negotiated rates.