DeepSeek V4 Pro API Pricing: $0.66 Off-Peak, $1.32 Peak

DeepSeek V4 Pro now costs $0.66 per million input tokens off-peak and $1.32 at peak, with output at $1.98 and $3.96, following the price increase that took effect August 16, 2026 at 16:00 UTC. The flat-rate era ended with it: DeepSeek now bills by time of day, with off-peak set at half the peak rate. Until the change, V4 Pro ran at $0.435 input and $0.87 output, rates that survived the model's exit from preview on August 12 by only four days.

On September 10, 2026, DeepSeek launched V4.1 Flash and announced that from September 14 every request to deepseek-v4-pro would be routed to V4.1 Flash and billed at V4.1 Flash rates, $0.15 input and $0.60 output off-peak. It then reversed that decision on user demand, so V4 Pro stays on the official API at the same billing. The new model is covered in DeepSeek V4.1 Flash API pricing. This page covers the V4 Pro rates, the August increase, and what a repricing this sharp says about how token prices actually work. The short version: the cheapest flagship API on the market raised prices up to 1,100 percent on ten days' notice, then said it would route the model away four weeks later and reversed that within days, and buyers had no instrument to lock either the rate or the product.

DeepSeek V4 Pro official API pricing

Peak hours are 01:00 to 04:00 and 06:00 to 10:00 UTC, Monday through Friday; everything else, including weekends and Chinese public holidays in full, bills off-peak at half the peak rate.

The cache-hit discount survived in relative terms, cache hits still cost about 3 percent of a cache miss, but the absolute cached rate rose more than 10x, from $0.003625 to $0.022 off-peak. The 1M context window still carries no surcharge.

Both models support JSON output, tool calls, and Anthropic API compatibility. V4.1 Flash replaced V4 Flash on the official API on September 10, 2026. Both columns are current.

What changed at GA

On price, nothing. The 0813 build is the first flagship DeepSeek release to exit preview with its preview pricing intact.

On the model itself, V4 Pro is a mixture-of-experts system with 1.6 trillion total parameters and 49 billion active per token. DeepSeek reports that its compressed attention design cuts inference compute to 27 percent of V3.2's at maximum context, with KV cache requirements at 10 percent. Those two engineering numbers are the economic story: they are why a 1M-context flagship can list at $0.435 at all. DeepSeek also reports benchmark results for the Pro Max mode including 80.6 percent on SWE-bench Verified and 93.5 percent on LiveCodeBench.

For how infrastructure efficiency translates into token prices generally, see why token prices differ across providers.

The DeepSeek V4 Pro price increase: what changed on August 16

The new rates took effect August 16, 2026 at 16:00 UTC, replacing the single flat rate with peak and off-peak billing. V4 Pro input on a cache miss went from $0.435 to $0.66 off-peak and $1.32 at peak. Output went from $0.87 to $1.98 and $3.96. Across the V4 line, the increases range from roughly 50 percent to over 1,100 percent depending on model, token type, and time of day.

This is worth sitting with, because it is a clean illustration of how posted prices work. A posted price is not a market price. It is a number one seller chooses, and it can move by announcement, in either direction, at any time. DeepSeek cut V3.2 prices repeatedly through 2025 and 2026. It has now made the opposite move, from a position where its official API is already among the cheapest hosts of its own model.

For buyers, the practical readings are now concrete. Cost models built on $0.435 input broke overnight; the same workload now costs 64 percent more off-peak and over 3x at peak. Cache-heavy workloads were hit hardest, since the near-free cached rate rose more than 10x. And third-party hosts, who set prices independently, re-sorted within three weeks: the cheap ones (GMI Cloud, StreamLake, Novita) repriced upward toward the new official peak, while DigitalOcean entered at $0.87 input and $1.74 output, below the official peak on both sides and below off-peak on output. The full provider table is on the DeepSeek V4 API pricing page.

What a real workload pays now

Take a production workload of 10M input tokens and 1M output tokens per day.

// text
Same workload, 10M input + 1M output tokens per day:

Before August 16 (flat rate):
No caching:        $5.22/day   ($1,905/year)
60% cache hits:    $2.63/day   ($961/year)

After August 16 (off-peak):
No caching:        $8.58/day   ($3,132/year)
60% cache hits:    $4.75/day   ($1,734/year)

After August 16 (peak):
No caching:        $17.16/day  ($6,263/year)
60% cache hits:    $9.50/day   ($3,468/year)

The same workload now costs 64 percent more if it runs entirely off-peak, and 3.3x more at peak. The spread between the best case (off-peak, cached) and worst case (peak, uncached) is now wider than the entire old bill. Two lessons survived the reprice: the blended rate is still what you actually pay, and as the V3.2 analysis showed, cache terms still dominate the blend. What's new is that the clock now matters too: scheduling batch work off-peak is worth an automatic 50 percent discount.

V4 Pro across providers

As of November 6, 2026, 21 providers list the V4 Pro 0813 build across 25 endpoints on OpenRouter, with input from $0.10 to $1.98 per million tokens and output from $1.74 to $8.00. The table below is the October 13 snapshot; the paragraphs after it carry the November 6 figures.

The official peak rate has become the reference price. Eight third-party hosts list at exactly $1.32 input and $3.96 output, the same as DeepSeek at peak, and none of them offer an off-peak discount. A buyer on one of those hosts pays the peak rate around the clock.

As of November 6, three hosts sit below the official off-peak input rate of $0.66: Relace at $0.10, Wafer at $0.117 and $0.285 on two endpoints, and Alibaba Cloud at $0.581. Only Alibaba is also below the official off-peak output rate, at $1.742. Ionstream has dropped off the listing and Sail Research has repriced to $1.35 input. For an uncached workload of 10M input and 1M output tokens per day, Wafer runs about $5.83 a day and Alibaba about $7.55, against $8.58 on the official API off-peak and $17.16 at peak; Relace's $8.00 output rate puts it at $9.00, above the official off-peak rate despite the lowest input price on the board. For cache-heavy workloads the answer flips. DeepSeek's cached input rate of $0.022 off-peak is a fraction of what the cheapest hosts charge, so at a 90 percent cache hit rate the official API off-peak costs about $2.84 a day on that workload, roughly tied with Alibaba at $2.85 and well below Wafer at $5.78.

Three listings carry a marked promotion, at 50, 25, and 20 percent off. Those are temporary prices. Budget at the list rate behind them, which is the official peak rate in all three cases, or lock capacity before the discount ends, which is what a forward contract is for.

One more thing to check before comparing hosts: OpenRouter still lists the April preview build, V4 Pro 0423, as a separate model with its own hosts and prices. Confirm which build a host serves before you compare its rate to the table above. Every DeepSeek model and host is on DeepSeek API pricing.

The re-sort after August happened fast. GMI Cloud, StreamLake, and Novita sat at $0.59 to $0.63 before the increase and moved to $1.03 to $1.60 within three weeks, tracking the new official peak rather than the old flat rate. Which prices move, and when, is exactly the kind of question a posted-price system answers slowly and a live market answers continuously.

The window, in hindsight

The decision window lasted ten days from DeepSeek's first warning on August 6, and only three days from August 13, when the actual rates were published, to August 16, when they took effect. During it, there was no way to lock the old economics: the official API sells at posted prices with no term structure, so buyers could only watch the date approach. Anyone budgeting a year of V4 Pro at August 15 rates woke up to a bill that is 64 to 230 percent higher. The routing notice repeated the pattern. DeepSeek said on September 10 that V4 Pro traffic would move to V4.1 Flash on September 14, four days' notice and a different model at the end of them. It reversed the plan before the date, which is its own lesson: terms can change in either direction on days' notice.

This is the structural gap forward markets exist to fill. When a seller can reprice by announcement, a buyer with a forward curve can price that risk and lock delivery months ahead; a buyer facing a posted price cannot. Physically settled token forwards are the instrument built for exactly this, and repricings like this one are the reason demand for them is growing. The Token Index tracks where V4 Pro and other open-weight models actually trade as the market re-sorts.

Frequently asked questions

What does DeepSeek V4 Pro cost right now?
As of November 6, 2026, unchanged since August 16: $0.66 per million input tokens off-peak and $1.32 at peak (cache miss), $0.022 to $0.044 on cache hits, and $1.98 to $3.96 per million output tokens. Peak hours are 01:00-04:00 and 06:00-10:00 UTC, Monday through Friday. The 1M context window carries no surcharge. DeepSeek had planned to route deepseek-v4-pro requests to V4.1 Flash from September 14, 2026, then kept V4 Pro live at these rates after user demand.

When did prices increase, and by how much?
August 16, 2026 at 16:00 UTC. V4 Pro input went from $0.435 to $0.66 off-peak and $1.32 peak; output from $0.87 to $1.98 and $3.96. Cached input rose more than 10x. DeepSeek also moved from a flat rate to peak/off-peak billing, with off-peak at half of peak. DeepSeek warned of an increase on August 6 without figures and published the rates on August 13, three days before they took effect.

Who is the cheapest DeepSeek V4 Pro host after the increase?
It depends on caching. For uncached workloads, Wafer ($0.117 input, $4.66 output) and Alibaba Cloud ($0.581 input, $1.742 output) undercut the official API at every hour as of November 6, 2026. For cache-heavy workloads, the official DeepSeek API off-peak is cheapest, because its cached input rate of $0.022 is far below what third-party hosts charge. Eight hosts list at exactly the official peak rate of $1.32 and $3.96 with no off-peak discount.

Is V4 Pro GA pricing different from preview pricing?
No. The 0813 GA build kept preview pricing unchanged.

Should I use V4 Pro or V4 Flash?
V4 Flash was retired on September 10, 2026. Its replacement, V4.1 Flash, lists at $0.15/$0.60 off-peak with the same 1M context window, and DeepSeek says it beats V4 Pro on performance, speed, and cost. Test V4.1 Flash on your actual task. If it passes, you cut your bill by about 4x on input and 3x on output. If it fails, V4 Pro is still on the official API, and third-party hosts serve the weights too.

Methodology

Official pricing verified against DeepSeek's API documentation on August 13, 2026. Release details from DeepSeek's V4 Pro 0813 general availability announcement. Post-increase rates verified against DeepSeek's API documentation. Third-party provider range from OpenRouter's V4 Pro page on September 2, 2026. V4.1 Flash rates and the V4 Pro routing rule verified against DeepSeek's API documentation and release notice on September 10, 2026. Official rates rechecked against DeepSeek's API documentation and third-party listings read from OpenRouter's V4 Pro 0813 page on October 13, 2026; the host table reflects that date. Host count, range, cheapest-host figures, and the official rate rechecked against OpenRouter's V4 Pro 0813 endpoint data on November 6, 2026. Last verified: 2026-11-06.