DeepSeek Pricing 2026: V4-Flash & V4-Pro API Costs

DeepSeek API pricing at a glance

The API exposes two models. DeepSeek-V4.1-Flash went generally available on 9 September 2026 and is served by the model name deepseek-flash; the older deepseek-v4-flash and deepseek-v4-flash-vision-exp names are still accepted but those models are retired and their requests are served by V4.1-Flash at the Flash price. DeepSeek-V4-Pro (deepseek-v4-pro) continues past 14 September 2026 with unchanged billing. The legacy names deepseek-chat and deepseek-reasoner were retired on 24 July 2026 at 15:59 UTC and are fully inaccessible — see deepseek-reasoner retired: migrate to V4-Flash, not Pro.

Table 1 — Current DeepSeek API rates, per 1M tokens, USD. Peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday; all other hours are off-peak. Verified 2026-09-18.

Need to wire this up in code? See the DeepSeek API setup guide.

How context caching cuts your bill

DeepSeek automatically caches the prefix of your prompts on disk. When a new request repeats a prefix it has recently seen — a system prompt, a long document, a few-shot example set — those repeated input tokens are billed at the much lower cache-hit rate instead of the cache-miss rate. This is automatic: no SDK changes, no cache-control headers, no opt-in flag. DeepSeek shipped disk-based context caching on 2 August 2024, and it has applied to every model generation since — including V4.

The practical impact is large for any workload with a stable prefix. If 90% of your input tokens are cache hits on V4.1-Flash, your effective off-peak input price drops from $0.15 to roughly $0.018 per 1M — an ~88% saving on input, with no code changes. To maximise it: keep the reusable part of your prompt (system instructions, context documents) at the front, and the variable part at the end.

Peak-hour pricing: now live on the official rate card

DeepSeek's old off-peak discount — 16:30–00:30 UTC daily, 50% off DeepSeek-V3 and 75% off DeepSeek-R1 — applied to the V3/R1 generation, not to V4. It ended with those models: the deepseek-chat and deepseek-reasoner aliases were retired on 24 July 2026 at 15:59 UTC.

What replaced it is the opposite. Since the DeepSeek-V4.1-Flash general-availability release, the official rate card carries two tiers: off-peak rates are exactly half of peak rates, so peak hours are a 100% surcharge. Peak applies Monday to Friday only, in these two windows:

Every other hour — including all day Saturday and Sunday — is off-peak, and the off-peak rows in Table 1 apply. That is 35 peak hours out of a 168-hour week, so a workload spread evenly across the whole week pays roughly 21% more than the off-peak rate; one that avoids both windows pays nothing extra.

Worked examples

How DeepSeek billing works

DeepSeek bills on tokens, not on requests or seats. Every API call is charged for its input tokens (your prompt, system message and any supplied context) plus its output tokens (the model's completion); in thinking mode, reasoning tokens are billed as output. A token is roughly ¾ of an English word — 1M tokens is about 750,000 words. There is no monthly minimum and no per-seat fee: you pay for exactly what you send and receive, deducted post-paid from your prepaid balance.

Rate limits: concurrency only

DeepSeek does not publish requests-per-minute (RPM) or tokens-per-minute (TPM) limits — neither figure appears anywhere in its documentation. The only documented ceiling is concurrency: how many requests you may have in flight at once.

There are no account tiers. Limits do not rise automatically with paid usage or account age — a higher concurrency ceiling requires an explicit capacity expansion request to DeepSeek. If you hit a 429 Too Many Requests, reduce the number of in-flight requests, retry with exponential back-off, and queue rather than fan out. If you need a permanently higher ceiling, contact DeepSeek to request expanded capacity.

V4-Flash vs V4-Pro: which should you use?

Default to V4-Flash. It handles the vast majority of production workloads — chat, RAG, extraction, classification, translation, tool-calling — at a fraction of Pro's cost and with the same 1M-token context window. On typical mixed workloads, Flash is roughly 3× cheaper end-to-end than Pro.

Escalate to V4-Pro only for calls that measurably fail on Flash: multi-step reasoning, competitive-math or code-golf problems, long-horizon agent planning, and heavy self-debugging coding sessions. A common cost-effective pattern is hybrid routing — send every call to Flash first, and re-run on Pro only when a confidence check, evaluation model, or user thumb-down flags the answer as insufficient.

For a deeper capability breakdown, see the DeepSeek V4 model guide.

DeepSeek pricing at scale

The gap widens dramatically at production volumes. A team running 100M tokens/day on V4.1-Flash (roughly 70M input at an 80% cache-hit ratio plus 30M output) pays roughly $610/month at off-peak rates. The same token volume on a US frontier API runs into the tens of thousands of dollars per month — run your own numbers against the rate table below rather than trusting a headline multiple.

The three levers that matter most for cost control at scale: (1) route to V4.1-Flash by default, (2) engineer prompts so the reusable prefix comes first for maximum cache-hit rate, and (3) schedule non-latency-critical batch work outside the two peak windows — that alone halves the rate on every token it moves. Together those three moves typically cut a naive DeepSeek bill by 60–80%.

DeepSeek pricing vs ChatGPT and Claude (2026)

Input / output rates per 1M tokens, verified 2026-07-25. Competitor rates change frequently — verify each provider's current pricing before committing.

For full feature breakdowns see our DeepSeek vs ChatGPT and DeepSeek vs Claude comparisons.

How we keep this page accurate

Pricing pages are only useful when the numbers are current. All rates on this page come from a single rate-config file in our codebase — the table, the calculator and the "last verified" stamp cannot drift out of sync, because they all read the same source. The date shown above is the last time a human editor confirmed the numbers, not the date this page was rebuilt.

Two layers: an automated job compares DeepSeek's official API pricing page against our rate-config every week and flags differences. When it flags something — or on our own review — an editor cross-checks the standing per-token rates, the cache-hit vs cache-miss columns, and the status of the announced peak-hour surcharge, updates the rate-config and the "Last verified" date, and notes the change in the blog changelog.

deepseek.ai is not affiliated with DeepSeek. If you spot a stale number, email us via the contact page — corrections typically ship the same day.

How to start using DeepSeek

Frequently asked questions