100,000 DeepSeek V4 Flash Vision Exp tokens cost $0.044 as input or $0.132 as output. Most workloads land in between — a 70/30 input/output split costs about $0.0704. Verified Aug 28, 2026
100,000 tokens is the rough size of a substantial codebase slice, a long report, or a busy production hour — about 21 chat-style requests (4,000 input + 800 output tokens each). Billed on DeepSeek V4 Flash Vision Exp at $0.44/M input and $1.32/M output, that volume costs $0.044 as pure input, $0.132 as pure output, or about $0.0704 at a typical 70/30 mix. Cached input is $0.014/M — 97% cheaper — so repeated system prompts and history can cut the input portion dramatically. As a budget-tier model it is priced for high-volume traffic — this is the volume range where it shines.
Interactive calculator
100,000 in · 0 out
Input price
$0.44 / 1M tokens
Output price
$1.32 / 1M tokens
Uncached pricing. Add caching and monthly projections in the full calculator.
What 100,000 tokens buys in practice
$0.0616
80% input / 20% output — short replies over conversation history.
$0.0528
90% input / 10% output — long retrieved context, grounded answers.
$0.0484
95% input / 5% output — full documents in, structured extraction out.
Same 100,000 tokens on other models
Related calculations
FAQ
100,000 input tokens cost $0.044; 100,000 output tokens cost $0.132. A typical 70/30 input/output mix costs about $0.0704. Rates: $0.44/M input, $1.32/M output.
A chat-style request of ~4,800 tokens (4,000 in + 800 out) means 100,000 tokens is roughly 21 requests. For a RAG workload with ~8,500 tokens per request, about 12 requests.
Yes — cached input costs $0.014/M instead of $0.44/M, a 97% discount on repeated context.