DeepSeek V4 Pro · DeepSeek

What does DeepSeek V4 Pro cost to run in a coding agent?

DeepSeek V4 Pro costs about $0.030 per average coding-agent request on our measured traffic, at list prices of $1.32 per million input and $3.96 per million output tokens. It scores 36 on the Artificial Analysis Intelligence Index, 24th of the 48 models we track. Source: Artificial Analysis (artificialanalysis.ai)

List prices: DeepSeek API pricing, checked 2026-10-13. Request costs: Standard Compute gateway data, 79,301 coding-agent requests from 75 users, Sep 13 to Oct 12, 2026. How we compute this

Run DeepSeek V4 Pro in your agent

Or let the router send each step to the cheapest model that can do it, on providers we vet for price, uptime and speed. Plans from $19 a month.

See plans

What DeepSeek V4 Pro costs per coding-agent request

Cost at list price	DeepSeek V4 Pro
Prompt under 100K tokens50% of requests, 87% of input cached	$0.014
Prompt of 100K to 272K39% of requests, 88% of input cached	$0.036
Prompt over 272K tokens11% of requests, 86% of input cached	$0.084
Average request	$0.030
100 requests	$3.04
Median session16 requests; a session ends after 10 idle minutes	$0.41
A month of regular usemedian of 20 users active on 5+ days	$42.42

Each logged request priced at the vendor’s list rates for its own token counts, including cache reads and any higher rate for long prompts. Average output: 698 tokens per request.

DeepSeek V4 Pro benchmarks, speed and latency

Artificial Analysis	Value	Rank
Intelligence Index10 evaluations, 0 to 100	36	24 of 48
Terminal-Bench 4.0agentic coding in a terminal	14.1%	21 of 39
Output speedmedian	99 tokens/s	19 of 44
Time to first answer tokenincludes thinking time	22 s	11 of 44

Source: Artificial Analysis (artificialanalysis.ai). Measured variant: DeepSeek V4 Pro 0813 (Max), speed on DeepSeek. Fetched October 13, 2026. Rank is among the models on this site, older versions included. Artificial Analysis runs Terminal-Bench 4.0 in its own setup, so its scores differ from the tbench.ai leaderboard.

About DeepSeek V4 Pro

DeepSeek V4 Pro is the larger model in DeepSeek's V4 line, with open weights and a 1M-token context; the current version dates from August 13, 2026. DeepSeek V4.1 Flash, released a month later, scores higher and costs less: Artificial Analysis gives V4 Pro 36 on its Intelligence Index and 14.1% in its Terminal-Bench 4.0 run, against 39 and 26.8% for V4.1 Flash, and V4 Pro costs about four and a half times as much per request in our measurements ($0.030 vs $0.0067 at peak rates). Open weights still make it an option for self-hosting.

Sources: Artificial Analysis

DeepSeek V4 Pro FAQ

How much does DeepSeek V4 Pro cost per coding-agent request?

$0.030 on average at list price, $3.04 per 100 requests, and $0.41 for a median 16-request session. That is 79,301 real coding-agent requests (Sep 13 to Oct 12, 2026) priced at DeepSeek's list rates; the median request sent 99,534 input tokens, 87% of input was read from cache, and requests returned 698 output tokens on average.

Does DeepSeek V4 Pro charge more for long prompts?

No. DeepSeek V4 Pro bills the same rate per token up to its 1M-token context window.

How fast is DeepSeek V4 Pro?

Artificial Analysis measures DeepSeek V4 Pro 0813 (Max) at 99 output tokens per second, with 22 seconds to the first answer token, thinking time included, on DeepSeek's API. Source: Artificial Analysis (artificialanalysis.ai).

Is DeepSeek V4 Pro good for AI agents?

Self-hosted setups that want DeepSeek's larger V4 model. On our scoring, which is calibrated to public benchmarks, it rates 6.1/10 for agentic ability and 7.2/10 for output quality. Open weights, self-hostable.

What is DeepSeek V4 Pro's context window?

DeepSeek V4 Pro has a 1.0M-token context window, large enough to hold sizeable codebases or document sets in a single run. DeepSeek is the maker.

Is DeepSeek V4 Pro open source?

Yes. DeepSeek V4 Pro ships with open weights, so you can self-host it or run it through a hosted provider such as OpenRouter. Check the license before commercial use.

What are the downsides of DeepSeek V4 Pro?

The main trade-offs: DeepSeek V4.1 Flash scores higher and costs less than a quarter as much per request; Hosted throughput varies by provider. It's strongest for self-hosted setups that want DeepSeek's larger V4 model.