DeepSeek

deepseek-v4-flash API Pricing

DeepSeek charges $0.15 per 1M input tokens and $0.60 per 1M output tokens across a 1M context window. Verified 2026-09-15 against the official DeepSeek pricing page.

Cache-miss off-peak rate; cache-hit input $0.003 off-peak; peak hours 01:00-04:00 and 06:00-10:00 UTC (Mon-Fri) double all rates

Input / 1M tokens

$0.15

Output / 1M tokens

$0.60

Context window

1M

What it costs to run

WorkloadTokensCost
Single short call2K in, 500 out$0.00060
Typical chat turn10K in, 1K out$0.00210
Long document pass100K in, 2K out$0.016
1,000 chat turns10M in, 1M out$2.10

Price history

Input price has moved +7% since tracking began on 2026-06-11.

EffectiveInput / 1MOutput / 1M
2026-09-15$0.15$0.60
2026-08-17$0.22$0.66
2026-06-11$0.14$0.28

How it compares

Ranked on the blended cost of a typical chat turn (10K in, 1K out), not the input rate alone.

OpenAIgpt-5-nano$0.00090 per turn
Googlegemini-2.0-flash-lite$0.00105 per turn
Googlegemini-2.5-flash-lite$0.00140 per turn
OpenAIgpt-4.1-nano$0.00140 per turn
DeepSeekdeepseek-v4-flash$0.00210 per turn
OpenAIgpt-5.6-luna$0.00320 per turn
OpenAIgpt-5.4-nano$0.00325 per turn
Googlegemini-3.1-flash-lite$0.00400 per turn
OpenAIbabbage-002$0.00440 per turn
OpenAIgpt-5-mini$0.00450 per turn

Head to head

Full cost breakdowns against the models deepseek-v4-flash is usually weighed against, including the workload shape where the cheaper option flips.

TechFastForward coverage of deepseek-v4-flash

What we wrote when this model, or the rest of its line, was news.

Free JSON API

Every tracked model, including this one, is available as JSON. Free to use with attribution and a link back.

curl https://techfastforward.com/api/data/llm-pricing

Maintained by Jordan Hale, TechFastForward. Prices are read daily from the official provider page and recorded only when they move. See every tracked model on the LLM API Pricing Tracker.