Models / OpenAI / GPT-5.1 Codex mini

OpenAI · gpt-codex

GPT-5.1 Codex mini

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

$0.25 in · $2.00 out

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

Provider input prices run from $0.20 to $0.25 per 1M tokens. Output prices run from $1.60 to $2.00.

Context
400,000
Max output
128,000
Cache read
$0.025
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
No
License
—
Released
Nov 13, 2025
Updated in source
Nov 13, 2025
Knowledge
2024-09-30
Providers
10

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$0.20$1.60$0.024——
DevPass$0.25$2.00$0.025——
Eden AIreference$0.25$2.00$0.025——
Impossibl$0.25$2.00$0.025——
Kilo Gateway$0.25$2.00$0.03——
LLM Gateway$0.25$2.00$0.025——
NanoGPT$0.25$2.00$0.025——
OpenRouter$0.25$2.00$0.03——
OrcaRouter$0.25$2.00$0.025——
Vercel AI Gateway$0.25$2.00$0.03——

Jobs this model qualifies for