ModelPickr

Models / Google / Gemini 2.5 Pro

Google · gemini-pro

Gemini 2.5 Pro

Google's proven reasoning model for coding, math, and multimodal analysis

$1.25 in · $10.00 out

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

Provider input prices run from $1.25 to $1.50 per 1M tokens. Output prices run from $9.96 to $10.00.

Context
1,048,576
Max output
65,536
Cache read
$0.13
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
No
License
—
Released
Jun 17, 2025
Updated in source
Jun 17, 2025
Knowledge
2025-01
Providers
22

Higher rates apply above 200,000 input tokens. The calculator switches to that rate when the input is longer.

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. 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
Abacus$1.25$10.00$0.13——
Auriko$1.25$10.00$0.13——
CrossModel$1.25$10.00$0.13$1.25—
Databricks$1.25$10.00$0.13——
DevPass$1.25$10.00$0.13——
Googlereference$1.25$10.00$0.13——
Impossibl$1.25$10.00$0.13——
Kilo Gateway$1.25$10.00$0.13$0.38—
LLM Gateway$1.25$10.00$0.13——
Merge Gateway$1.25$10.00$0.13——
Modelis$1.25$10.00———
NanoGPT$1.25$10.00$0.13$0.38—
NEAR AI Cloud$1.25$10.00$0.13——
Ofox$1.25$10.00$0.13$4.50—
OpenRouter$1.25$10.00$0.13$0.38—
OrcaRouter$1.25$10.00$0.13——
Requesty$1.25$10.00$0.31$2.38—
SAP AI Core$1.25$10.00$0.13——
Vercel AI Gateway$1.25$10.00$0.13——
Vertex$1.25$10.00$0.13—deprecated
Cortecs$1.50$9.96$0.24$0.43—
AnyAPI—————

Jobs this model qualifies for