ModelPickr

Models / DeepSeek / DeepSeek R1 0528

DeepSeek · deepseek-thinking

DeepSeek R1 0528

May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning

$0.70 in · $2.50 out

per 1M tokens · provider rate closest to the median. No first-party DeepSeek price was listed. The reference price is Kilo Gateway's rate, the provider closest to the median.

Provider input prices run from $0.50 to $1.35 per 1M tokens. Output prices run from $2.15 to $5.40.

Context
163,840
Max output
32,768
Cache read
$0.35
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
No
Open weights
Yes
License
MIT
Released
May 28, 2025
Updated in source
May 28, 2025
Knowledge
—
Providers
5

Hugging Face weights

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
OpenRouter$0.50$2.15$0.35——
Eden AI$0.66$2.60$0.17——
Kilo Gatewayreference$0.70$2.50$0.35——
Novita AI$0.70$2.50$0.35——
Merge Gateway$1.35$5.40$0.95——

Jobs this model qualifies for