DeepSeek R1 (0528) · DeepSeek

What does DeepSeek R1 (0528) cost to run in a coding agent?

DeepSeek R1 (0528) costs about $0.031 per average coding-agent request on our measured traffic, at OpenRouter's listed prices of $0.50 per million input and $2.15 per million output tokens. It scores 13 on the Artificial Analysis Intelligence Index (an estimate), 44th of the 48 models we track. Source: Artificial Analysis (artificialanalysis.ai)

List prices: OpenRouter listed price, 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 current Claude, GPT, Gemini and open models 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 R1 costs per coding-agent request

Cost at list price	DeepSeek R1
Prompt under 100K tokens50% of requests, 87% of input cached	$0.023
Prompt of 100K to 272K39% of requests, 88% of input cached	$0.049
Prompt over 272K tokens11% of requests, 86% of input cached	n/a
Average request	$0.031
100 requests	$3.06
Median session16 requests; a session ends after 10 idle minutes	$0.29
A month of regular usemedian of 20 users active on 5+ days	$30.90

Each logged request priced at the listed rates above for its own token counts, including cache reads and any higher rate for long prompts. Average output: 698 tokens per request. 28% of requests were larger than DeepSeek R1's 164K context window and are left out of its figures.

DeepSeek R1 benchmarks, speed and latency

Artificial Analysis	Value	Rank
Intelligence Index10 evaluations, 0 to 100	13 (estimate)	44 of 48
Output speedmedian	28 tokens/s	44 of 44
Time to first answer tokenincludes thinking time	73 s	27 of 44

Source: Artificial Analysis (artificialanalysis.ai). Measured variant: DeepSeek R1 0528 (May '25). 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.

What to watch for

Its 164K-token window is smaller than 28% of our coding-agent requests, which are left out of the figures above, so long agent sessions will hit the limit. Cached input costs $0.35 per million, 70% of its input price, so agent traffic, which is mostly cache reads, gets little discount. The price is OpenRouter's listed rate on October 13, 2026, which can be a third-party host's; DeepSeek's own API may charge differently.

About DeepSeek R1 (0528)

DeepSeek R1 (0528) is the May 28, 2025 update of DeepSeek's open-weight reasoning model, the line that made long chain-of-thought widely available. It has since been overtaken: Artificial Analysis estimates 13 on its Intelligence Index, measures about 28 output tokens per second, and lists it as superseded. Its 164K context is smaller than 27.9% of the coding-agent requests we measured. DeepSeek V4.1 Flash scores 39 and costs less per request ($0.0067 vs $0.031).

Sources: Artificial Analysis

DeepSeek R1 (0528) FAQ

How much does DeepSeek R1 (0528) cost per coding-agent request?

$0.031 on average at OpenRouter's listed price, $3.06 per 100 requests, and $0.29 for a median 16-request session. That is 79,301 real coding-agent requests (Sep 13 to Oct 12, 2026) priced at OpenRouter's listed 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 R1 (0528) charge more for long prompts?

No. DeepSeek R1 (0528) bills the same rate per token up to its 164K-token context window, which is smaller than 28% of the coding-agent requests we measured.

How fast is DeepSeek R1 (0528)?

Artificial Analysis measures DeepSeek R1 0528 (May '25) at 28 output tokens per second, with 73 seconds to the first answer token, thinking time included. Source: Artificial Analysis (artificialanalysis.ai).

Is DeepSeek R1 (0528) good for AI agents?

Research and comparisons that need the original R1 reasoning model. On our scoring, which is calibrated to public benchmarks, it rates 4.4/10 for agentic ability and 4.0/10 for output quality. Open weights.

What is DeepSeek R1 (0528)'s context window?

DeepSeek R1 (0528) has a 164K-token context window. DeepSeek is the maker.

Is DeepSeek R1 (0528) open source?

Yes. DeepSeek R1 (0528) 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 R1 (0528)?

The main trade-offs: Slow (about 28 output tokens/s, per Artificial Analysis); 164K context, smaller than 27.9% of the coding-agent requests we measured; Superseded by DeepSeek's V4 models. It's strongest for research and comparisons that need the original R1 reasoning model.