ModelPickr

Models / OpenAI / GPT-5-Codex

OpenAI · gpt-codex

GPT-5-Codex

Coding-optimized GPT model for repository edits, reviews, and agentic software work

$1.25 in · $10.00 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.

Context
400,000
Max output
128,000
Cache read
$0.13
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
No
License
—
Released
Sep 15, 2025
Updated in source
Sep 15, 2025
Knowledge
2024-09-30
Providers
3

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
Abacusreference$1.25$10.00$0.13——
Impossibl$1.25$10.00$0.13——
Vercel AI Gateway$1.25$10.00$0.13——