ModelPickr

Models / OpenAI / GPT-4o

OpenAI · gpt

GPT-4o

Omni-era GPT for multimodal chat, practical coding, and general assistants

$2.50 in · $10.00 out

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

Provider input prices run from $1.25 to $4.25 per 1M tokens. Output prices run from $5.00 to $17.00.

Context
128,000
Max output
16,384
Cache read
$1.25
Cache write
—
Reasoning
No
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
No
License
—
Released
May 13, 2024
Updated in source
Aug 6, 2024
Knowledge
2023-09
Providers
20

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-4o

$30.00

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. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
Cloudflare AI Gateway$1.25$5.00$0.63——
Ofox$2.00$8.00$1.00——
Abacus$2.50$10.00$1.25——
Azure$2.50$10.00$1.25—deprecated
Azure Cognitive Services$2.50$10.00$1.25—deprecated
DevPass$2.50$10.00$1.25——
Eden AI$2.50$10.00$1.25——
Impossibl$2.50$10.00$1.25——
Kilo Gateway$2.50$10.00$1.25——
LLM Gateway$2.50$10.00$1.25——
Merge Gateway$2.50$10.00$1.25——
NanoGPT$2.50$10.00$1.25——
OpenAIreference$2.50$10.00$1.25——
OpenRouter$2.50$10.00$1.25——
OrcaRouter$2.50$10.00$1.25——
Pioneer$2.50$10.00$1.25$2.50—
Prime Inference$2.50$10.00———
Cortecs$2.66$10.64$1.33——
AI/ML API$3.25$13.00$1.63——
Vercel AI Gateway$4.25$17.00$2.13——

Jobs this model qualifies for