Models / OpenAI / GPT-4

OpenAI · gpt

GPT-4

GPT model for general reasoning, writing, coding, and tool-assisted tasks

$30.00 in · $60.00 out

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

Provider input prices run from $30.00 to $39.00 per 1M tokens. Output prices run from $60.00 to $78.00.

Context
8,192
Max output
8,192
Cache read
—
Cache write
—
Reasoning
No
Tool calls
Yes
Structured output
No
Vision
No
Open weights
No
License
—
Released
Nov 6, 2023
Updated in source
Apr 9, 2024
Knowledge
2023-11
Providers
9

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.

Estimated monthly cost

GPT-4

$270

Cache hit is ignored because this model has no cache-read price.

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
DevPass$30.00$60.00———
Eden AI$30.00$60.00———
Kilo Gateway$30.00$60.00———
LLM Gateway$30.00$60.00———
Merge Gateway$30.00$60.00———
OpenAIreference$30.00$60.00——deprecated
OpenRouter$30.00$60.00———
OrcaRouter$30.00$60.00———
AI/ML API$39.00$78.00$39.00——