ModelPickr

Models / DeepSeek / DeepSeek-V3

DeepSeek · deepseek

DeepSeek-V3

Open DeepSeek MoE chat model for coding, math, and general reasoning

$0.32 in · $0.89 out

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

Provider input prices run from $0.27 to $0.89 per 1M tokens. Output prices run from $0.89 to $1.30.

Context
131,072
Max output
8,192
Cache read
—
Cache write
—
Reasoning
No
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
Yes
License
DeepSeek Model License
Released
Dec 26, 2024
Updated in source
Dec 26, 2024
Knowledge
—
Providers
6

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-V3

$3.26

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. One row per provider.
ProviderInputOutputCache readCache writeStatus
Merge Gateway$0.27$1.10———
Pioneer$0.27$1.12$0.14$0.27—
Deep Infrareference$0.32$0.89———
Eden AI$0.32$0.89———
Hugging Face$0.40$1.30———
Novita AI$0.89$0.89———

Jobs this model qualifies for