Models / DeepSeek / DeepSeek-R1

DeepSeek · deepseek-thinking

DeepSeek-R1

Classic open reasoning model for transparent math, coding, and deliberate problem solving

$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 Hugging Face's rate, the provider closest to the median.

Provider input prices run from $0.40 to $1.35 per 1M tokens. Output prices run from $1.70 to $5.40.

Context
128,000
Max output
32,768
Cache read
—
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
Yes
License
—
Released
Jan 20, 2025
Updated in source
May 29, 2025
Knowledge
2024-07
Providers
13

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.

Estimated monthly cost

DeepSeek-R1

$7.95

Cache hit is ignored because this model has no cache-read price.

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
NanoGPT$0.40$1.70$0.20——
Cloudflare Workers AI$0.50$4.88———
TensorX$0.66$2.60$0.17$0.83—
Melious$0.70$2.78$0.19——
Eden AI$0.70$2.40———
Hugging Facereference$0.70$2.50———
Kilo Gateway$0.70$2.50———
Novita AI$0.70$2.50———
OpenRouter$0.70$2.50———
Amazon Bedrock$1.35$5.40———
Merge Gateway$1.35$5.40———
Vercel AI Gateway$1.35$5.40———
Snowflake Cortex—————

Jobs this model qualifies for