Skip to content
CostPerPrompt

DeepSeek V3.1 Terminus API Pricing

DeepSeek · context window 164K · prices updated 2026-09-15

Input per 1M tokens
$0.27
Output per 1M tokens
$1.00
Cached input per 1M
$0.135
50% cheaper than fresh input

Where DeepSeek V3.1 Terminus sits on price

At $1.00 per million output tokens, DeepSeek V3.1 Terminus is a mid tier model — 2.1× cheaper than the median output price of $2.08, which puts it cheaper than 69% and pricier than 31% of the models we track. It sits 11th cheapest of the 18 DeepSeek models we track. Output costs 3.7× input, the usual spread — trim both, starting with the answer length.

Output tokens per $1
1,000,000
One full context fill
$0.0442
Cheaper than
69% of tracked models

Cached input is 50% cheaper. On an input-heavy workload you need roughly a 50% 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 V3.1 Terminus

These three workloads are the ones teams actually run on a mid-priced model — a $1.00/1M 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. $0.0027 $41.25
Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. $0.0013 $393
Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. $0.0003 $8.55

Model your exact traffic in the API cost calculator — it preloads DeepSeek V3.1 Terminus with caching and batch options.

DeepSeek V3.1 Terminus price history

DeepSeek last raised DeepSeek V3.1 Terminus's output price on Aug 21, 2026 (+5% per output token), from $0.27/$0.95 to $0.27/$1.00 per 1M in/out. That is one of 2 repricings in the 44 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) $0.27 $1.00
Aug 12, 2026 $0.27 $0.95 -5%
Aug 21, 2026 $0.27 $1.00 +5%

Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).

DeepSeek V3.1 Terminus vs Qwen2.5 VL 72B Instruct

The closest-priced alternative from another vendor is Qwen2.5 VL 72B Instruct (Alibaba (Qwen)) — priced within a rounding error on output, with $0.53 more 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 Qwen2.5 VL 72B Instruct pricing →

Cheaper alternatives

More DeepSeek models

Frequently asked questions

How much does the DeepSeek V3.1 Terminus API cost?

DeepSeek V3.1 Terminus costs $0.27 per million input tokens and $1.00 per million output tokens, with cached input at $0.135 per million (50% cheaper). That works out to roughly 1,000,000 output tokens per dollar.

What does the support chatbot workload cost on DeepSeek V3.1 Terminus?

Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.0027 per request and $41.25 per month on DeepSeek V3.1 Terminus. Conversation history re-sent each turn — the classic prompt-caching win.

What does it cost to fill DeepSeek V3.1 Terminus's 164K context window?

Sending 164K of input in a single request costs $0.0442 at $0.27 per million tokens — before any output. With prompt caching that same fill drops to about $0.0221 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.

Is DeepSeek V3.1 Terminus worth the price?

DeepSeek V3.1 Terminus sits in the middle of the market (11 of 18 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.