How much does DeepSeek V4 Pro cost per month?

For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, DeepSeek V4 Pro costs about $990.00 per month at the provider's official standard (peak) prices (verified) ($1.32 per 1M input tokens, $3.96 per 1M output tokens).

Does DeepSeek V4 Pro support prompt caching?

Yes. Cached input costs $0.044 per 1M tokens, compared with $1.32 for regular input.

How long is DeepSeek V4 Pro's context window?

DeepSeek V4 Pro accepts up to 1,000,000 tokens (1M) of context and returns up to 393,216 tokens per response.

Does DeepSeek V4 Pro have off-peak pricing?

Yes. Off-peak requests cost $0.66 per 1M input tokens and $1.98 per 1M output tokens, compared with $1.32 and $3.96 at the standard (peak) price. Off-peak is every hour outside 01:00–04:00 and 06:00–10:00 UTC on weekdays, plus weekends and Chinese public holidays.

DeepSeek V4 Pro API Pricing

DeepSeek · released Aug 12, 2026 · 1M context · API model ID deepseek-v4-pro

DeepSeek V4 Pro by DeepSeek API pricing: $1.32 per 1M input tokens and $3.96 per 1M output tokens (standard (peak) price, verified against the official pricing page, Oct 9, 2026).

Prices

DeepSeek V4 Pro prices, USD per 1M tokens
Price	USD per 1M tokens
Input	$1.32
Output	$3.96
Cache read	$0.044
Cache write	Not published
Off-peak input	$0.66
Off-peak output	$1.98
Off-peak cache read	$0.022

The Input, Output and Cache read rows are the standard (peak) prices; the Off-peak rows apply at other times. Off-peak is every hour outside 01:00–04:00 and 06:00–10:00 UTC on weekdays, plus weekends and Chinese public holidays.

Verified against the provider's official pricing page on Oct 9, 2026. Official pricing page

Estimated monthly cost

$990.00

per month

per day: $33.00
per request: $0.0033

Cost = input tokens × input price + output tokens × output price, 30 days a month. Cached input uses the cache read price. Cache write fees are not included. Estimates use the standard (peak) price. Off-peak usage costs less.

Compare this workload across models

Monthly cost by workload

Workload	Per month
Chatbot1,000 in / 500 out tokens, 10,000 requests a day	$990.00/mo
RAG8,000 in / 500 out tokens, 5,000 requests a day	$1,881/mo
Coding agent50,000 in / 2,000 out tokens, 1,000 requests a day, 80% cached input	$686.40/mo

Context and capabilities

Context: 1,000,000 tokens
Max output: 393,216 tokens
Input: text
Output: text
Knowledge cutoff: Not published
Open weights: Yes
Tool calling: Yes
Reasoning: Yes
Structured outputs: Yes

Capabilities and limits as listed by models.dev.

Similarly priced models

Muse Spark 1.3 · $1.25 in / $4.25 out · Compare
Gemini 3.8 Flash · $0.75 in / $3.75 out · Compare
Qwen3.8 Max · $2.00 in / $6.00 out · Compare
Mistral Medium 3.5 · $1.50 in / $7.50 out · Compare

Price history

No price changes since we started tracking on Oct 8, 2026.

Questions

How much does DeepSeek V4 Pro cost per month?: For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, DeepSeek V4 Pro costs about $990.00 per month at the provider's official standard (peak) prices (verified) ($1.32 per 1M input tokens, $3.96 per 1M output tokens).
Does DeepSeek V4 Pro support prompt caching?: Yes. Cached input costs $0.044 per 1M tokens, compared with $1.32 for regular input.
How long is DeepSeek V4 Pro's context window?: DeepSeek V4 Pro accepts up to 1,000,000 tokens (1M) of context and returns up to 393,216 tokens per response.
Does DeepSeek V4 Pro have off-peak pricing?: Yes. Off-peak requests cost $0.66 per 1M input tokens and $1.98 per 1M output tokens, compared with $1.32 and $3.96 at the standard (peak) price. Off-peak is every hour outside 01:00–04:00 and 06:00–10:00 UTC on weekdays, plus weekends and Chinese public holidays.