ModelPickr

Models / OpenAI / GPT-4o mini

OpenAI · gpt-mini

GPT-4o mini

Small omni GPT for cheap multimodal assistance and production-scale traffic

$0.15 in · $0.60 out

per 1M tokens · first-party price. Reference price from OpenAI, the lab's own listing.

Provider input prices run from $0.075 to $0.25 per 1M tokens. Output prices run from $0.30 to $1.00.

Context
128,000
Max output
16,384
Cache read
$0.075
Cache write
—
Reasoning
No
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
No
License
—
Released
Jul 18, 2024
Updated in source
Jul 18, 2024
Knowledge
2023-09
Providers
23

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
Cloudflare AI Gateway$0.075$0.30$0.038——
Ofox$0.12$0.48$0.06——
Abacus$0.15$0.60———
Azure$0.15$0.60$0.075—deprecated
Azure Cognitive Services$0.15$0.60$0.075—deprecated
CrossModel$0.15$0.60$0.075$0.15—
DevPass$0.15$0.60$0.075——
Eden AI$0.15$0.60$0.075——
Impossibl$0.15$0.60$0.075——
Kilo Gateway$0.15$0.60$0.075——
LLM Gateway$0.15$0.60$0.075——
Merge Gateway$0.15$0.60$0.075——
NanoGPT$0.15$0.60$0.075——
OpenAIreference$0.15$0.60$0.075——
OpenRouter$0.15$0.60$0.075——
OrcaRouter$0.15$0.60$0.075——
Pioneer$0.15$0.60$0.075$0.15—
Prime Inference$0.15$0.60———
Cortecs$0.16$0.64$0.081——
Requesty$0.17$0.66$0.083——
Venice AI$0.19$0.75$0.094——
AI/ML API$0.20$0.78$0.098——
Vercel AI Gateway$0.25$1.00$0.13——

Jobs this model qualifies for