Models / OpenAI / GPT-5.2 Codex

OpenAI · gpt-codex

GPT-5.2 Codex

Code-specialist GPT for repository edits, reviews, and long-running software agents

$1.75 in · $14.00 out

per 1M tokens · provider rate closest to the median. No first-party OpenAI price was listed. The reference price is Abacus's rate, the provider closest to the median.

Provider input prices run from $1.40 to $1.75 per 1M tokens. Output prices run from $11.20 to $14.00.

Context
400,000
Max output
128,000
Cache read
$0.18
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
No
License
—
Released
Dec 11, 2025
Updated in source
Dec 11, 2025
Knowledge
2025-08-31
Providers
11

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
Ofox$1.40$11.20$0.14——
Abacusreference$1.75$14.00$0.18——
DevPass$1.75$14.00$0.18——
Eden AI$1.75$14.00$0.18——
Impossibl$1.75$14.00$0.18——
Kilo Gateway$1.75$14.00$0.18——
LLM Gateway$1.75$14.00$0.18——
NanoGPT$1.75$14.00$0.18——
OpenRouter$1.75$14.00$0.18——
OrcaRouter$1.75$14.00$0.18——
Vercel AI Gateway$1.75$14.00$0.18——

Jobs this model qualifies for