Until August 16, DeepSeek V4 Pro cost $0.435 per million input tokens and $0.87 per million output tokens on the official DeepSeek API. Sixteen providers host it, and here is the unusual part: the official API was the cheapest of all of them. Third-party hosts charged anywhere from $0.59 to $1.74 per million input tokens for the same model, up to 4x the developer's own rate.
That is the exact opposite of the pattern on GLM-5.2, where the official API anchors the expensive end and discounters undercut it by 95 percent. Same market, same year, inverted structure. This page covers the full provider table, the cache discount that makes the official rate even harder to beat, the V4 Flash budget sibling, and how V4 stacks against V3.2.
Since this page was written, DeepSeek launched V4.1 Flash on September 10, 2026, retired V4 Flash, and announced that V4 Pro traffic routes to V4.1 Flash from September 14. Rates and routing details are in DeepSeek V4.1 Flash API pricing.
For the V4 Pro deep dive, see the dedicated DeepSeek V4 Pro API pricing page, and for every DeepSeek model and host in one place, DeepSeek API pricing.
What DeepSeek V4 is, briefly
Released April 24, 2026, DeepSeek V4 Pro is the flagship successor to the V3 line: an open-weight model with a 1M-token context window (up from V3.2's 163K), tool calling, and prompt caching, serving at roughly 63 tokens per second with a 1.33s time to first token. On public benchmark aggregates it sits in the 80th percentile for general intelligence.
It shipped alongside DeepSeek V4 Flash, which was retired on September 10, 2026 and replaced by V4.1 Flash at $0.15 input and $0.60 output off-peak on the official API.
DeepSeek V4 official API pricing
| Token type | V4 Pro off-peak | V4 Pro peak | V4.1 Flash off-peak | V4.1 Flash peak |
|---|---|---|---|---|
| Input (cache miss) $/1M | $0.66 | $1.32 | $0.15 | $0.30 |
| Input (cache hit) $/1M | $0.022 | $0.044 | $0.003 | $0.006 |
| Output $/1M | $1.98 | $3.96 | $0.60 | $1.20 |
Peak hours are 01:00 to 04:00 and 06:00 to 10:00 UTC, Monday through Friday; all other hours, including weekends, bill at off-peak rates, which are half of peak. The famous 99 percent cache discount survived the increase in relative terms (cache hits still run about 3 percent of the cache-miss rate), but in absolute terms cached input rose more than 10x, the steepest single increase in the new schedule.
DeepSeek V4 Pro pricing by provider: all 16 hosts
| Provider | Input $/1M | Output $/1M | Cached input $/1M |
|---|---|---|---|
| DeepSeek (official, off-peak) | $0.66 | $1.98 | $0.022 |
| DigitalOcean | $0.87 | $1.74 | $0.174 |
| StreamLake | $1.027 | $2.055 | $0.086 |
| Baidu Qianfan | $1.029 | $2.058 | $0.085 |
| GMI Cloud | $1.044 | $2.088 | $0.087 |
| Ionstream | $1.131 | $2.262 | $0.094 |
| CoreWeave | $1.15 | $2.55 | $0.20 |
| DeepInfra | $1.30 | $2.60 | $0.10 |
| DeepSeek (official, peak) | $1.32 | $3.96 | $0.044 |
| Alibaba | $1.416 | $2.832 | $0.118 |
| SiliconFlow | $1.502 | $3.135 | $0.135 |
| Novita | $1.60 | $3.20 | $0.135 |
| Venice | $1.65 | $3.301 | $0.33 |
| AtlasCloud | $1.68 | $3.38 | $0.13 |
| NextBit | $1.72 | $3.45 | $0.14 |
| BaseTen | $1.74 | $3.48 | $0.145 |
| Parasail | $1.74 | $3.48 | $0.10 |
| Azure (US) | $1.91 | $3.83 | $0.16 |
Until August 16, this table had an unusual structure: the official API was the cheapest of all 16 hosts. The new pricing ends that, but only at peak. Off-peak, DeepSeek is still the cheapest on input and cached tokens, and only DigitalOcean beats it on output. At peak ($1.32 / $3.96), seven hosts undercut it on input and all sixteen on output. The hosts that used to sit just above DeepSeek at $0.59 to $0.63 (GMI Cloud, StreamLake, Novita) repriced up to $1.03 to $1.60 within three weeks of the change, while DigitalOcean entered as the low bidder. Prices as of September 2, 2026.
Why the developer was the cheapest host
Two markets, opposite structures, one explanation: who is trying to win the traffic.
Z.AI prices GLM-5.2 at a premium and lets third parties compete for volume. DeepSeek does the reverse: it prices its own API at or near serving cost and treats third-party hosts as overflow. For a lab that runs its own highly optimized inference stack, underpricing every reseller is a deliberate strategy, it keeps the traffic, the usage data, and the customer relationship at home. Third parties serving V4 Pro carry their own GPU economics plus margin, and without a price advantage they compete on other grounds: enterprise terms, data residency, platform integration, bundling.
The lesson for buyers is that "official vs third-party" has no fixed answer. It flips model by model, which is why rate-card assumptions ported from one model to another keep being wrong, the pattern documented across the whole market in Why Token Prices Differ.
What a real workload pays
The first table below is the pre-increase reference. At current rates the same workload costs $8.58 a day on the official API off-peak, $17.16 at peak, and $10.44 on DigitalOcean, the cheapest third party. The full current comparison is on DeepSeek API pricing.
A production assistant doing 10M input and 1M output tokens per day on V4 Pro:
| Provider | Daily | Monthly | Annual |
|---|---|---|---|
| DeepSeek official | $5.22 | $156.60 | $1,905 |
| Mid-tier host (Cloudflare, $1.15/$2.55) | $14.05 | $421.50 | $5,128 |
| Top-tier host ($1.74/$3.48) | $20.88 | $626.40 | $7,621 |
Now add a 60 percent cache hit rate on input:
| Provider | Daily with 60% cached input |
|---|---|
| DeepSeek official, off-peak ($0.022 cached) | $4.75 |
| DigitalOcean ($0.174 cached) | $6.26 |
| DeepSeek official, peak ($0.044 cached) | $9.50 |
With caching, the official API still wins off-peak: its $0.022 cached rate is 4x to 8x cheaper than any third party's, so the cache-heavy version of this workload pays $4.75 a day on DeepSeek off-peak against $6.26 on DigitalOcean. At peak it flips, $9.50 on DeepSeek versus $6.26. For pure cost, V4 Pro is now a schedule question, not a host question. The remaining reasons to pay a premium third party are compliance, latency, region, or platform.
And if the workload doesn't need reasoning: V4.1 Flash off-peak at $0.15/$0.60 runs the same 10M/1M day for $2.10 on the official API. The retired V4 Flash weights still run it for $0.66 a day from the cheapest third-party host. From September 14 the question is moot on the official API, since V4 Pro requests are served by V4.1 Flash anyway.
DeepSeek V4 vs V3.2 vs GLM-5.2
| V4 Pro | V3.2 | GLM-5.2 | |
|---|---|---|---|
| Official input / output $/1M | $0.66–$1.32 / $1.98–$3.96 | Retired from official API (was $0.28 / $0.42) | $1.40 / $4.40 |
| Best available input $/1M | $0.66 (official, off-peak) | ~$0.20 (3rd party) | $0.07 (3rd party) |
| Official cached input $/1M | $0.022–$0.044 | $0.028 | $0.26 |
| Context window | 1M | 163K | 1M |
| Cheapest host | Official off-peak, third party at peak | Third party | Third party |
| Cross-host spread | ~3x | ~3x | 30x |
Three models, three completely different market structures. The only reliable way to buy is to run your own token mix against current rates, which is what the blended benchmarks on the Mercatus Token Index exist for. For the V3.2 breakdown, see DeepSeek V3.2 API Pricing.
How to choose a V4 provider
- Cost, off-peak traffic: the official API, especially with caching. Cost, peak traffic: DigitalOcean at $0.87 / $1.74 or StreamLake at $1.03 / $2.06. Around the clock it is roughly a tie, so split routing by hour if you can.
- Long-context workloads: the 1M window is native; confirm third parties serve the full window before paying their premium for other reasons.
- No reasoning required: V4.1 Flash at $0.15/$0.60 off-peak, which is also where V4 Pro traffic lands from September 14.
- Compliance, region, or platform needs: the 4x premium at the top of the table is what those requirements currently cost on this model. Price it explicitly rather than absorbing it silently.
- Recheck monthly. V3.2's market compressed and GLM's collapsed within a quarter of launch; V4's structure is four months old and will move too.
Frequently asked questions
How much does DeepSeek V4 cost per million tokens?
As of August 16, 2026: V4 Pro costs $0.66 input and $1.98 output off-peak, doubling to $1.32 and $3.96 at peak hours (01:00-04:00 and 06:00-10:00 UTC). V4.1 Flash, which replaced V4 Flash on September 10: $0.15/$0.60 off-peak, $0.30/$1.20 peak. Cached input runs $0.022-$0.044 for Pro.
Who is the cheapest DeepSeek V4 provider?
Off-peak, the official DeepSeek API at $0.66 input. At peak, DigitalOcean at $0.87 input and $1.74 output, followed by StreamLake and Baidu Qianfan at about $1.03 / $2.06. On output, DigitalOcean's $1.74 is below the official rate at every hour.
Why do third parties charge more than the official API?
DeepSeek prices its own API near serving cost to keep traffic first-party. Third-party hosts carry their own GPU costs plus margin, so without a price edge they compete on enterprise terms, regions, and platform features instead.
What is the difference between V4 Pro and V4 Flash?
Pro is the flagship with reasoning capability at $0.66/$1.98 off-peak. V4 Flash was the lower-cost variant and was retired on September 10, 2026. Its successor V4.1 Flash lists at $0.15/$0.60 off-peak, carries the same 1M-token context window, and takes over V4 Pro traffic on the official API from September 14. Both carry the 1M-token context window.
Is DeepSeek V4 cheaper than V3.2?
No. V3.2 is no longer sold on the official API (the deepseek-chat name was retired July 24), but on third-party hosts it runs about $0.20 input against V4 Pro's $0.66/$1.98 off-peak.
How does V4's provider spread compare to other models?
About 3x on V4 Pro ($0.66 to $1.91 input) after third parties repriced, versus about 3x on V3.2 and 30x on GLM-5.2. V4 Flash is wider at 6.5x on input and 7.9x on output because most hosts held the old official price when DeepSeek moved.
Methodology
Provider pricing compiled from published rate cards and public pricing trackers (sourced from OpenRouter and Helicone data), September 2026. Benchmark percentiles from public aggregates. Workload examples use stated token volumes and cache assumptions; recompute with your own mix. V3.2 and GLM-5.2 comparison figures from the corresponding Mercatus pricing pages. Official rates reflect DeepSeek's peak/off-peak schedule effective August 16, 2026. Third-party rates are from OpenRouter's V4 Pro page on September 2, 2026 and include any promotional discounts in effect that day. V4.1 Flash rates and the V4 Pro routing rule verified against DeepSeek's API documentation on September 10, 2026. Last verified: 2026-09-10.