Skip to content
CostPerPrompt

DeepSeek V4 Pro 0813 API Pricing

DeepSeek · context window 1M · prices updated 2026-09-29

Input per 1M tokens
$0.48
Output per 1M tokens
$4.20
Cached input per 1M
$0.384
20% cheaper than fresh input

Where DeepSeek V4 Pro 0813 sits on price

At $4.20 per million output tokens, DeepSeek V4 Pro 0813 is a mid tier model — 1.9× the median output price of $2.20, which puts it cheaper than 37% and pricier than 63% of the models we track. It is the most expensive of the 15 DeepSeek models we track. Output costs 8.8× more than input here, so anything that makes the model write less — tighter instructions, structured output, lower max_tokens — moves the bill more than trimming the prompt.

Output tokens per $1
238,095
One full context fill
$0.5033
Cheaper than
37% of tracked models

Cached input is 20% cheaper. On an input-heavy workload you need roughly a 100% 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 0813

These three workloads are the ones teams actually run on a mid-priced model — a $4.20/1M 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. $0.0083 $124
Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. $0.0035 $1062
Long-context analysis — 200 runs/day (250K in / 4K out) Only possible on large-context models; input cost is nearly the whole bill. $0.1368 $821

Model your exact traffic in the API cost calculator — it preloads DeepSeek V4 Pro 0813 with caching and batch options.

DeepSeek V4 Pro 0813 price history

DeepSeek last raised DeepSeek V4 Pro 0813's output price on Sep 29, 2026, from $0.3995/$4.20 to $0.48/$4.20 per 1M in/out. That is one of 19 repricings in the 47 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 13, 2026 (tracking began) $0.435 $0.87 —
Aug 17, 2026 $1.32 $3.96 +355%
Aug 21, 2026 $1.19 $3.56 -10%
Aug 23, 2026 $1.12 $3.37 -6%
Aug 28, 2026 $0.66 $1.98 -41%
Sep 2, 2026 $1.12 $3.35 +69%
Sep 5, 2026 $1.12 $3.36 0%
Sep 7, 2026 $1.05 $3.15 -6%
Sep 11, 2026 $0.66 $1.98 -37%
Sep 12, 2026 $0.5782 $1.73 -12%
Sep 14, 2026 $0.9834 $2.95 +70%
Sep 17, 2026 $0.66 $1.98 -33%
Sep 19, 2026 $0.5782 $1.73 -12%
Sep 20, 2026 $0.66 $1.98 +14%
Sep 23, 2026 $0.4987 $1.50 -24%
Sep 24, 2026 $0.462 $1.39 -7%
Sep 26, 2026 $0.264 $0.792 -43%
Sep 27, 2026 $0.245 $3.50 +342%
Sep 28, 2026 $0.3995 $4.20 +20%
Sep 29, 2026 $0.48 $4.20 0%

Change-points from our daily price snapshots (tracking since Aug 13, 2026; intraday moves between snapshots are not captured).

DeepSeek V4 Pro 0813 vs Qwen3 VL 235B A22B Thinking

The closest-priced alternative from another vendor is Qwen3 VL 235B A22B Thinking (Alibaba (Qwen)) — 5% cheaper on output, with $0.08 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 Qwen3 VL 235B A22B Thinking pricing →

Cheaper alternatives

More DeepSeek models

Frequently asked questions

› How much does the DeepSeek V4 Pro 0813 API cost?

DeepSeek V4 Pro 0813 costs $0.48 per million input tokens and $4.20 per million output tokens, with cached input at $0.384 per million (20% cheaper). That works out to roughly 238,095 output tokens per dollar.

› What does the support chatbot workload cost on DeepSeek V4 Pro 0813?

Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.0083 per request and $124 per month on DeepSeek V4 Pro 0813. Conversation history re-sent each turn — the classic prompt-caching win.

› What does it cost to fill DeepSeek V4 Pro 0813's 1M context window?

Sending 1M of input in a single request costs $0.5033 at $0.48 per million tokens — before any output. With prompt caching that same fill drops to about $0.4027 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.

› Is DeepSeek V4 Pro 0813 worth the price?

DeepSeek V4 Pro 0813 sits in the middle of the market (15 of 15 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.