ModelPickr

Models / Anthropic / Claude Sonnet 4.5

Anthropic · claude-sonnet

Claude Sonnet 4.5

Balanced Claude model for coding, analysis, agent workflows, and cost control

$3.00 in · $15.00 out

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

Context
200,000
Max output
64,000
Cache read
$0.30
Cache write
$3.75
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
Yes
Open weights
No
License
—
Released
Sep 29, 2025
Updated in source
Sep 29, 2025
Knowledge
2025-07-31
Providers
10

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$3.00$15.00———
Amazon Bedrock$3.00$15.00$0.30$3.75—
Anthropicreference$3.00$15.00$0.30$3.75—
Databricks$3.00$15.00$0.30$3.75—
DevPass$3.00$15.00$0.30$3.75—
LLM Gateway$3.00$15.00$0.30$3.75—
Merge Gateway$3.00$15.00$0.30$3.75—
Tempr Gateway$3.00$15.00$0.30$3.75—
Vertex$3.00$15.00$0.30$3.75—
Vertex$3.00$15.00$0.30$3.75deprecated

Jobs this model qualifies for