DeepSeek V4 Pro 0423 API Pricing
DeepSeek · context window 1M · prices updated 2026-09-07
Where DeepSeek V4 Pro 0423 sits on price
At $1.91 per million output tokens, DeepSeek V4 Pro 0423 is a mid tier model — 1.2× cheaper than the median output price of $2.20, which puts it cheaper than 56% and pricier than 44% of the models we track. It sits 12th cheapest of the 16 DeepSeek models we track. Output is only 2.0× the input price, an unusually flat spread: long prompts hurt about as much as long answers, so prompt size is where the savings are.
Cached input is 92% cheaper. On an input-heavy workload you need roughly a 27% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.
What real workloads cost on DeepSeek V4 Pro 0423
These three workloads are the ones teams actually run on a mid-priced model — a $1.91/1M model is not bought for the same job as one ten times the price.
| Workload | Per request | Per month |
|---|---|---|
| Support chatbot — 500 conversations/day (5K in / 1.4K out) Conversation history re-sent each turn — the classic prompt-caching win. | $0.0075 | $112 |
| Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. | $0.0038 | $1146 |
| Long-context analysis — 200 runs/day (250K in / 4K out) Only possible on large-context models; input cost is nearly the whole bill. | $0.2465 | $1479 |
Model your exact traffic in the API cost calculator — it preloads DeepSeek V4 Pro 0423 with caching and batch options.
DeepSeek V4 Pro 0423 price history
DeepSeek last raised DeepSeek V4 Pro 0423's output price on Sep 7, 2026 (+35% per output token), from $0.7078/$1.42 to $0.9553/$1.91 per 1M in/out. That is one of 18 repricings in the 36 days we have tracked it — worth knowing before you hard-code today's rate into a budget.
| Date | Input /1M | Output /1M | Output change |
|---|---|---|---|
| Aug 2, 2026 (tracking began) | $0.435 | $0.87 | — |
| Aug 11, 2026 | $0.6317 | $1.26 | +45% |
| Aug 12, 2026 | $1.17 | $2.34 | +85% |
| Aug 17, 2026 | $1.32 | $3.96 | +70% |
| Aug 21, 2026 | $1.60 | $3.20 | -19% |
| Aug 22, 2026 | $0.4475 | $0.8951 | -72% |
| Aug 23, 2026 | $0.3969 | $0.7938 | -11% |
| Aug 24, 2026 | $0.5262 | $1.05 | +33% |
| Aug 25, 2026 | $0.7903 | $1.58 | +50% |
| Aug 26, 2026 | $0.87 | $1.74 | +10% |
| Aug 28, 2026 | $0.7416 | $1.48 | -15% |
| Aug 29, 2026 | $0.6809 | $1.36 | -8% |
| Aug 30, 2026 | $0.4273 | $0.8547 | -37% |
| Aug 31, 2026 | $1.04 | $2.08 | +144% |
| Sep 1, 2026 | $1.60 | $3.20 | +54% |
| Sep 2, 2026 | $1.04 | $2.08 | -35% |
| Sep 5, 2026 | $0.9107 | $1.82 | -13% |
| Sep 6, 2026 | $0.7078 | $1.42 | -22% |
| Sep 7, 2026 | $0.9553 | $1.91 | +35% |
Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).
DeepSeek V4 Pro 0423 vs GLM 5
The closest-priced alternative from another vendor is GLM 5 (Z.ai (GLM)) — priced within a rounding error on output, with $0.3553 less per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.
See GLM 5 pricing →Cheaper alternatives
More DeepSeek models
Frequently asked questions
› How much does the DeepSeek V4 Pro 0423 API cost?
DeepSeek V4 Pro 0423 costs $0.9553 per million input tokens and $1.91 per million output tokens, with cached input at $0.0796 per million (92% cheaper). That works out to roughly 523,423 output tokens per dollar.
› What does the support chatbot workload cost on DeepSeek V4 Pro 0423?
Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.0075 per request and $112 per month on DeepSeek V4 Pro 0423. Conversation history re-sent each turn — the classic prompt-caching win.
› What does it cost to fill DeepSeek V4 Pro 0423's 1M context window?
Sending 1M of input in a single request costs $1.00 at $0.9553 per million tokens — before any output. With prompt caching that same fill drops to about $0.0835 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.
› Is DeepSeek V4 Pro 0423 worth the price?
DeepSeek V4 Pro 0423 sits in the middle of the market (12 of 16 by price within DeepSeek). The honest test is a routing experiment: send the same 200 real requests to this model and to a tier below, and compare failure rate against the price gap — most teams find a majority of traffic never needed the pricier model.