DeepSeek API pricing
Compare 3 DeepSeek models in the TokenCOGS registry, then run the same workload through the cost calculators.
DeepSeek model pricing table
USD per 1M text tokens. Live pricing is checked against the central TokenCOGS registry when this page loads.
| Model | Input | Output | Cached input | Context | |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | $0.194 | $0.775 | $0.0039 | 1M tokens | Details → |
| DeepSeek V4 Flash legacy alias | $0.194 | $0.775 | $0.0039 | 1M tokens | Calculate → |
| DeepSeek V4 Pro | $0.853 | $2.5575 | $0.0284 | 1M tokens | Details → |
Current DeepSeek savings programs
No verified provider-specific credits or promotions are currently stored in the TokenCOGS registry.
Price is only the first filter
Use this table to eliminate models that do not fit your unit economics, then benchmark the remaining candidates on your own task for output quality, latency, rate limits and operational reliability.
DeepSeek V4.1 Flash currently has the lowest blended input-token price in this DeepSeek set. V4 Pro remains available after September 14, 2026 under DeepSeek’s latest changelog; an earlier phase-out notice was reversed. That does not automatically make it the lowest-cost model for every workload because output ratios, caching, long-context rules and tool usage can change the result.