DeepSeek V4.1 Flash vs DeepSeek V4 Pro pricing
- For the Chatbot workload, DeepSeek V4.1 Flash costs 3.7× less than DeepSeek V4 Pro.
- For the RAG workload, DeepSeek V4.1 Flash costs 4.2× less than DeepSeek V4 Pro.
- For the Coding agent workload, DeepSeek V4.1 Flash costs 4.1× less than DeepSeek V4 Pro.
Prices
| USD per 1M tokens | DeepSeek V4.1 Flash | DeepSeek V4 Pro |
|---|---|---|
| Input | $0.30 | $1.32 |
| Output | $1.20 | $3.96 |
| Cache read | $0.006 | $0.044 |
| Cache write | Not published | Not published |
| Batch input | Not published | Not published |
| Batch output | Not published | Not published |
| Off-peak input | $0.15 | $0.66 |
| Off-peak output | $0.60 | $1.98 |
| Off-peak cache read | $0.003 | $0.022 |
DeepSeek V4.1 Flash: 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.
DeepSeek V4 Pro: 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
Monthly cost by workload
| Workload | DeepSeek V4.1 Flash | DeepSeek V4 Pro |
|---|---|---|
| Chatbot1,000 in / 500 out tokens, 10,000 requests a day | $270.00/mo | $990.00/mo |
| RAG8,000 in / 500 out tokens, 5,000 requests a day | $450.00/mo | $1,881/mo |
| Coding agent50,000 in / 2,000 out tokens, 1,000 requests a day, 80% cached input | $169.20/mo | $686.40/mo |
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.
Context and capabilities
| DeepSeek V4.1 Flash | DeepSeek V4 Pro | |
|---|---|---|
| Context | 1,000,000 tokens | 1,000,000 tokens |
| Max output | 393,216 tokens | 393,216 tokens |
| Input | text, image | text |
| Tool calling | Yes | Yes |
| Reasoning | Yes | Yes |
| Structured outputs | Yes | Yes |
Questions
- What is the price difference between DeepSeek V4.1 Flash and DeepSeek V4 Pro?
- DeepSeek V4.1 Flash: $0.30 per 1M input tokens and $1.20 per 1M output tokens. DeepSeek V4 Pro: $1.32 per 1M input tokens and $3.96 per 1M output tokens. For the Chatbot workload (1,000 in / 500 out tokens, 10,000 requests a day), that is about $270.00 per month for DeepSeek V4.1 Flash and $990.00 for DeepSeek V4 Pro.
- Which has the longer context window, DeepSeek V4.1 Flash or DeepSeek V4 Pro?
- Both accept up to 1,000,000 tokens of context.
- Do DeepSeek V4.1 Flash and DeepSeek V4 Pro have prompt caching and batch prices?
- DeepSeek V4.1 Flash: cached input $0.006 per 1M tokens; no batch price published. DeepSeek V4 Pro: cached input $0.044 per 1M tokens; no batch price published.