DeepSeek V4 Pro API pricing
Of the 13 providers checked, Aurora Inference lists the lowest blended rate for DeepSeek V4 Pro: $1.00 input and $2.00 output per 1M tokens, on its pricing page as of 25 September 2026.
The general-availability release of DeepSeek V4 Pro, replacing the preview. It is a large text-only model with 1.6T parameters, 49B of them active per token. DeepSeek's own API charges half price outside peak hours, which is why this page lists off-peak rates separately.
Across 13 providers, the most expensive charges 3.0Γ the cheapest on a blended basis.
Prices by provider
Per 1M tokens, on-demand, sorted cheapest first by blended cost (3:1 input to output). Off-peak and long-context rates are listed on each provider's page.
| # | Provider | Input / 1M | Cached / 1M | Output / 1M | Checked | Notes |
|---|---|---|---|---|---|---|
| 1 | $1.00 | $0.10 | $2.00 | 25 Sep 2026 | Listed as deepseek/deepseek-v4-pro | |
| 2 | $1.04 | $0.0352 | $2.08 | 3 Oct 2026 | Listed as the 0813 snapshot of DeepSeek V4 Pro. | |
| 3 | $1.30 | $0.10 | $2.60 | 25 Sep 2026 | ||
| 4 | $1.32 | β | $3.96 | 25 Sep 2026 | International region, deepseek-v4-pro-0813, busy hours; idle hours are half price | |
| 5 | $1.32 | $0.132 | $3.96 | 25 Sep 2026 | Listed as DeepSeek V4 Pro 0813 | |
| 6 | $1.32 | $0.044 | $3.96 | 25 Sep 2026 | @cf/deepseek-ai/deepseek-v4-pro-0813 | |
| 7 | $1.32 | $0.044 | $3.96 | 25 Sep 2026 | Peak rate; off-peak hours are half price | |
| 8 | $1.32 | $0.044 | $3.96 | 25 Sep 2026 | Standard tier; listed as DeepSeek V4 Pro (0813) | |
| 9 | $1.32 | $0.044 | $3.96 | 25 Sep 2026 | Listed as DeepSeek V4 Pro 0813 | |
| 10 | $1.32 | $0.044 | $3.96 | 25 Sep 2026 | Listed as DeepSeek-V4-Pro-0813 | |
| 11 | $1.32 | $0.13 | $3.96 | 25 Sep 2026 | Listed as DeepSeek V4 Pro 0813 | |
| 12 | β¬2.01 β $2.2848 | β¬0.51 | β¬4.03 β $4.5809 | 1 Oct 2026 | ||
| 13 | β¬2.62 β $2.9782 | β¬0.66 | β¬5.23 β $5.9449 | 1 Oct 2026 | Listed in SimpleCredits (100 SC = EUR 1); homepage advertises 20% off during the open beta |
Each price was read off the provider's own pricing page on the date shown; the date links to that page. Providers that publish no per-token price for this model are not listed. EUR prices are ranked at the ECB reference rate of 24 September 2026. The same data is open under CC-BY at /api/query/prices.
Of the 3 European-headquartered providers checked, Aurora Inference lists the lowest blended rate for DeepSeek V4 Pro: $1.00 input and $2.00 output per 1M tokens, on its pricing page as of 25 September 2026.
European providers
Per 1M tokens, on-demand, for providers headquartered in Europe, sorted cheapest first by blended cost (3:1 input to output). See all European AI providers
| # | Provider | Input / 1M | Cached / 1M | Output / 1M | Checked | Notes |
|---|---|---|---|---|---|---|
| 1 | $1.00 | $0.10 | $2.00 | 25 Sep 2026 | Listed as deepseek/deepseek-v4-pro | |
| 2 | β¬2.01 β $2.2848 | β¬0.51 | β¬4.03 β $4.5809 | 1 Oct 2026 | ||
| 3 | β¬2.62 β $2.9782 | β¬0.66 | β¬5.23 β $5.9449 | 1 Oct 2026 | Listed in SimpleCredits (100 SC = EUR 1); homepage advertises 20% off during the open beta |
Each price was read off the provider's own pricing page on the date shown; the date links to that page. Providers that publish no per-token price for this model are not listed. EUR prices are ranked at the ECB reference rate of 24 September 2026. The same data is open under CC-BY at /api/query/prices.
Need a yes/no, a choice or a score rather than text? See decision models.
Compare every inference provider on free tiers, hosting and EU availability in the inference APIs table.
Is your product missing?