Home › Providers › DeepSeek
DeepSeek API pricing
V4 Pro and V4.1 Flash, open weights. 2 models priced per 1,000,000 tokens, verified October 2026. Cheapest: DeepSeek V4.1 Flash at $0.30 input. Most expensive: DeepSeek V4 Pro at $3.96 output.
DeepSeek price table
| Model | Input | Cached | Cache write | Output | Context | Batch |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | $0.30 | $0.006 | — | $1.20 | 1,100,000 | No |
| DeepSeek V4 Pro | $1.32 | $0.044 | — | $3.96 | 1,000,000 | No |
How DeepSeek compares with other providers
| Provider | Models | Cheapest input | Cheapest output | Flagship output |
|---|---|---|---|---|
| OpenAI | 13 | $0.10 | $0.50 | $50 |
| Anthropic | 5 | $1 | $5 | $50 |
| Google Gemini | 6 | $0.30 | $2.50 | $12 |
| xAI Grok | 2 | $1.25 | $2.50 | $6 |
| DeepSeek | 2 | $0.30 | $1.20 | $3.96 |
Workload cost on DeepSeek
| Model | Support chat 1K reqs · 4K/600 | RAG + cache 1K reqs · 50K/1K | Nightly batch 10K reqs · 10K/2K |
|---|---|---|---|
| DeepSeek V4.1 Flash | $1.92 | $2.98 | $54 |
| DeepSeek V4 Pro | $7.66 | $12.60 | $211 |
FAQ
What is the cheapest DeepSeek model?
DeepSeek V4.1 Flash at $0.30 per 1M input and $1.20 per 1M output tokens.
What is the most expensive DeepSeek model?
DeepSeek V4 Pro at $1.32 per 1M input and $3.96 per 1M output tokens.
Does DeepSeek charge for prompt caching?
Yes. Cached reads are published per model; on this provider they range from $0.006 to $0.044 per 1M tokens.