Models / OpenAI / o3

OpenAI · o

o3

Deliberate o-series reasoner for hard math, coding, and multi-step analysis

$2.00 in · $8.00 out

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

Provider input prices run from $2.00 to $3.50 per 1M tokens. Output prices run from $8.00 to $14.00.

Context
200,000
Max output
100,000
Cache read
$0.50
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
No
License
—
Released
Apr 16, 2025
Updated in source
Apr 16, 2025
Knowledge
2024-05
Providers
18

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

o3

$24.00

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. One row per provider.
ProviderInputOutputCache readCache writeStatus
302.AI$2.00$8.00———
Abacus$2.00$8.00$0.50——
AIHubMix$2.00$8.00$0.50——
Azure$2.00$8.00$0.50——
Azure Cognitive Services$2.00$8.00$0.50——
Cloudflare AI Gateway$2.00$8.00$0.50——
DevPass$2.00$8.00$0.50——
Eden AI$2.00$8.00$0.50——
Impossibl$2.00$8.00$0.50——
Kilo Gateway$2.00$8.00$0.50——
LLM Gateway$2.00$8.00$0.50——
Merge Gateway$2.00$8.00$0.50——
NanoGPT$2.00$8.00$1.00——
NEAR AI Cloud$2.00$8.00$0.50——
OpenAIreference$2.00$8.00$0.50——
OpenRouter$2.00$8.00$0.50——
Vercel AI Gateway$3.50$14.00$0.88——
AnyAPI—————

Jobs this model qualifies for