DeepSeek V4 Flash API pricing

DeepSeek's fast, ultra-cheap tier with a 1M-token context window — half price off-peak.

Tool callingReasoningPrompt caching

Input

$0.44

per 1M tokens

Cached input

$0.014

per 1M tokens

Output

$1.32

per 1M tokens

Context window

1M

max output 384K

Prices last synced Aug 20, 2026 from the LiteLLM community price catalog — the same catalog Marginal prices real usage events against, refreshed daily. Hand-checked against the provider's official pricing page on Aug 20, 2026. Spot an error? Tell us.

Pricing notes

  • Rates shown are peak-hour (01:00–04:00 and 06:00–10:00 UTC). ALL other hours are off-peak at exactly half price: $0.22 input / $0.007 cached / $0.66 output per 1M.
  • Input is billed by cache outcome — a cache hit costs ~1/30th of a miss. Thinking and non-thinking modes cost the same.
  • 1M-token context, up to 384K output tokens.

Also sold by

Each host prices the model independently — same weights, different bill.

HostInput / 1MOutput / 1MContext
DeepSeek (first-party)$0.44$1.321M
Fireworks AI$0.14$0.281M

What would DeepSeek V4 Flash cost you?

Enter your workload — add other models to compare the same traffic across providers.

Your monthly workload

Cache hit rate = share of input tokens served from the provider's prompt cache, billed at the model's cached-input price. Estimates use standard per-token rates — batch discounts, service tiers, and long-context surcharges are not applied.

DeepSeek V4 Flash
ModelInputCached inputOutputPer requestMonthly
DeepSeek V4 Flash$264$5.60$330$0.00120$600
Rates used: DeepSeek V4 Flash $0.44 in / $1.32 out

Compare DeepSeek V4 Flash

More from DeepSeek

Tracking DeepSeek V4 Flash in production?

Marginal prices every call your app actually makes — cached tokens, dated snapshots, model switches included — and slices spend by customer or feature. One track() call to integrate.