Pricing Verified fallback snapshot · 41 models · 7 providers · verified September 3, 2026.
DeepSeek · Current

DeepSeek V4 Pro API pricing & cost

Current token rates, context limits, workload examples and unit-economics shortcuts for DeepSeek V4 Pro.

Input / 1M tokens$0.853
Output / 1M tokens$2.5575
Cached input / 1M$0.0284
Context window1M tokens

Pricing page fallback verified September 3, 2026; client checks TokenCOGS live registry on load.

Quick cost examples

What the token rates mean in dollars

Example workload: 2,000 input tokens + 500 output tokens per request, standard text-token pricing.

VolumeEstimated API costApprox. / request
1,000 requests$2.98$0.0030
100,000 requests$298.37$0.0030
1,000,000 requests$2,983.75$0.0030
Change the token assumptions →
Positioning

Where DeepSeek V4 Pro sits on price

DeepSeek V4 Pro sits toward the highest input-token rate in the current TokenCOGS registry for this provider. Price alone is not a quality ranking, but this position is useful when you are screening models for unit-economics fit before benchmarking latency and quality.

Cost comparison is not a quality, latency or reliability ranking. Benchmark the task you actually need to run.

Compare all DeepSeek models →
Cost considerations

What can move the invoice

  • Cached input is tracked at $0.0284 per 1M tokens, which can materially change repeated-system-prompt or repeated-context workloads.
  • Default TokenCOGS rate is a 24-hour weighted average using DeepSeek’s published 7 peak / 17 off-peak hours.
Current deals & credits

Ways this provider may reduce spend

No verified provider-specific credits or promotions are currently stored in the TokenCOGS registry.

Compare

Nearby DeepSeek options

ModelInput / 1MOutput / 1MContext
DeepSeek V4 Flash$0.284$0.8531M tokensCalculate
FAQ

DeepSeek V4 Pro pricing questions

How much does DeepSeek V4 Pro cost per 1M tokens?

The current TokenCOGS snapshot lists DeepSeek V4 Pro at $0.853 per 1M input tokens and $2.5575 per 1M output tokens. Live registry data can update these values when the provider changes pricing.

What would 1,000 DeepSeek V4 Pro requests cost?

At 2,000 input tokens and 500 output tokens per request, 1,000 requests are approximately $2.98 before provider-specific extras. Change the workload in the linked calculator for your own usage pattern.

Is DeepSeek V4 Pro the cheapest DeepSeek model?

DeepSeek V4 Pro sits toward the highest input-token rate in the current TokenCOGS registry for this provider. Price alone is not a quality ranking, but this position is useful when you are screening models for unit-economics fit before benchmarking latency and quality.