DeepSeek V4.1 Flash benchmarks

DeepSeek V4.1 Flash is an open-weights model from DeepSeek, released 10 Sep 2026. It ranks 27th of 51 on our overall leaderboard and 7th of 50 for value, though some of its results are not yet published. At A$0.74 per million tokens (blended), it costs about 4.9× cheaper than the median model we track. It writes about 231 tokens a second, and answers start after 9.5 s on average, thinking included. Its weights are public, so it can be hosted in Australia on your own infrastructure or an Australian cloud region.

#27 OF 51 OVERALLA$0.74 / 1M TOKENS1M CONTEXTUPDATED 23 SEP 2026
CONTEXT WINDOW
1,000,000 tokens
MAX OUTPUT
384,000 tokens
INPUT
text, image
WEIGHTS
Open (MIT)
RELEASED
10 Sep 2026
OUTPUT SPEED
231 tok/s
ANSWER STARTS AFTER
9.5 s (thinking included)
DEEPSEEK DOCS
§ 02 — RESULTS

Benchmark results.

Independent test scores are for the reasoning, max effort setting. “Among tracked” ranks DeepSeek V4.1 Flash against the 51 models on this site; LMArena ranks run across its full leaderboard.

ALL RESULTS5 OF 8 CORE SIGNALS
DeepSeek V4.1 Flash benchmark results
BENCHMARKRESULTAMONG TRACKEDSOURCE DETAIL
INDEPENDENT TESTS · ARTIFICIAL ANALYSIS
AA Intelligence Index39.5#23 of 51Reasoning, max effort
Humanity’s Last Exam39.2%#38 of 51Reasoning, max effort
AA-LCR84.0%#7 of 51Reasoning, max effort
SciCode51.9%#31 of 46Reasoning, max effort
BLIND HUMAN VOTES · LMARENA
LMArena WebDev3,125 votes · ±121616#13 of 45#17 of 129 on LMArena · 22 Sep 2026
LMArena Agent20,080 sessions#12#10 of 37#12 of 46 on LMArena · 15 Sep 2026
§ 03 — COST

What DeepSeek V4.1 Flash costs in Australian dollars.

List prices converted at the snapshot’s RBA rate, excluding GST. Reasoning models are billed for their thinking as output tokens, so heavier settings cost more than the job estimates show.

LIST PRICE
DeepSeek V4.1 Flash price per million tokens
PER MILLION TOKENSAUDUSD LIST
Input tokensA$0.42US$0.30
Output tokensA$1.68US$1.20
Blended (3 in : 1 out)A$0.74US$0.53
EVERYDAY JOBSESTIMATES
Estimated cost of common jobs in Australian dollars
JOBCOST (AUD)MEDIAN MODEL
Customer support replyPER 1,000 REPLIESA$1.35A$6.58
Summarise a 30-page documentPER 100 DOCUMENTSA$0.98A$4.74
Agentic coding taskPER 10 TASKSA$0.77A$3.72
§ 04 — AUSTRALIA

Running DeepSeek V4.1 Flash in Australia.

Its weights are public, so it can be hosted in Australia on your own infrastructure or an Australian cloud region. How the platforms compare →

AUSTRALIAN CLOUD REGIONS
DeepSeek V4.1 Flash availability in Australian cloud regions
PLATFORMAVAILABILITYDETAIL
AWS Bedrock · SydneyNOT OFFERED
AWS Bedrock · MelbourneNOT OFFERED
Azure · Australia EastNOT OFFERED
Google Vertex AI · SydneyNOT OFFERED
Your own infrastructureSELF-HOST

Open weights: run it on your own servers or GPU instances in an Australian region.

§ 06 — QUESTIONS

DeepSeek V4.1 Flash, answered.

DeepSeek V4.1 Flash lists at US$0.30 per million input tokens and US$1.20 per million output tokens — A$0.42 and A$1.68 at A$1 = US$0.7123 (RBA, 22 Sep 2026), excluding GST. A typical customer support reply works out at about A$1.35 per 1,000 replies, before any reasoning tokens.

DeepSeek V4.1 Flash’s weights are public, so it can be hosted in Australia on your own infrastructure or an Australian cloud region. Availability comes from the cloud providers’ own documentation; check your provider’s current terms before relying on it for data-residency obligations.

Artificial Analysis measures DeepSeek V4.1 Flash at about 231 tok/s of output, with the answer starting after 9.5 s on average once thinking time is included (reasoning, max effort setting).

DeepSeek documents a context window of 1,000,000 tokens (1M), with up to 384,000 output tokens. On AA-LCR, which tests reasoning across ~100,000-token document sets, it scores 84.0%.

PUT THE COMPARISON TO WORK

Need help choosing and using AI for your business?