Model Details
2026-06Price Data Last Verified: June 22, 2026
DeepSeek V4 Pro API Pricing & Cost Calculator
DeepSeek's higher-capacity current API model. The calculator uses the official cache-miss input rate.
Pricing Details
- Provider
- DeepSeek
- Input Price
- $0.435 / 1M tokens
- Output Price
- $0.87 / 1M tokens
- Context Window
- 1M
Official source: api-docs.deepseek.com
Official page also lists a cache-hit input rate of $0.003625 per 1M tokens.
Cost Scenarios
Detailed Cost Breakdown
| Scenario | Input Tokens | Output Tokens | Input Cost | Output Cost | Total Cost |
|---|---|---|---|---|---|
| Small Request | 1,000 | 1,000 | $0.0004 | $0.0009 | $0.0013 |
| Medium Request | 10,000 | 10,000 | $0.0044 | $0.0087 | $0.013 |
| Large Request | 100,000 | 50,000 | $0.0435 | $0.0435 | $0.087 |
| High Volume | 1,000,000 | 500,000 | $0.435 | $0.435 | $0.87 |
Other DeepSeek Models
Keep Evaluating
What to read before you lock in DeepSeek V4 Pro
DeepSeek V4 Pro vs DeepSeek V4 Flash
See the decision-ready pricing breakdown between DeepSeek V4 Pro and DeepSeek V4 Flash.
DeepSeek V4 Pro vs Claude Haiku 4.5
See the decision-ready pricing breakdown between DeepSeek V4 Pro and Claude Haiku 4.5.
DeepSeek V4 Pro vs Claude Opus 4.8
See the decision-ready pricing breakdown between DeepSeek V4 Pro and Claude Opus 4.8.
Choose the Right AI Model
Use a workload-first framework instead of picking the most famous model by default.
Token Calculation and Cost Estimation
Estimate token budgets before you commit a feature or pricing plan.
AI API Cost Optimization Guide
Reduce spend with routing, caching, batching, and model mix strategies.