Skip to content
← Leaderboard

DeepSeek V4.1 Flash 1017

Open source
Self-hostable
Free to run
DeepSeek
Open license
text
vision
Released 8d ago
Avg score
50.5
/ 100 · not enough data for the index
Context
1.0M
Output limit
393k
Input price
$0.15 /M
Output price
$0.60 /M
Parameters
763.2B · 188B active
Est. VRAM (Q4)
~457.9 GB

Price from the model maker's own API, verified 8h ago · cached input $0.0030 /M

Added automatically from the public model catalog. Family and licence details are not curated yet; benchmark scores appear as upstream leaderboards list this model.

Benchmarks

knowledge

SimpleQA VerifiedFresh
%

A human-validated factuality benchmark of short factual questions whose answers can be checked against a single ground truth. Penalises hallucinations by scoring confidently-wrong answers below abstentions.

math

OTIS Mock AIME 2024-2025Fresh
%

AIME-style competition problems written specifically for the OTIS mock contest, then run as an evaluation by Epoch AI. Closer in spirit to the public AIME but with novel problems unlikely to appear in training data.

reliability

API Success RateN/A
%

Share of nightly probe requests over the last 14 days that streamed a complete answer without an error, timeout or empty response. Needs at least five attempts before a figure is shown.

Reliability monitor

Loading drift signal…

Hosted endpoints

HostInput $/MOutput $/MContextSpeedTTFTUptime 24hQuant
Host 73$0.10$0.151.0M50 tok/s0.57 s100.0%fp4
Host 74$0.10$0.151.0M52 tok/s0.44 s100.0%fp4
Host 36$0.08$0.241.0M66 tok/s1.96 s77.3%fp8
Host 37$0.10$0.291.0M95 tok/s0.49 s99.6%fp8
Host 38$0.15$0.441.0M——100.0%fp8
Host 67$0.07$0.501.0M119 tok/s0.34 s100.0%unknown
Host 68$0.08$0.501.0M——100.0%fp8
Host 69$0.08$0.501.0M——100.0%fp8
Host 75$0.13$0.501.0M——100.0%mxfp4
Host 76$0.14$0.551.0M95 tok/s0.56 s99.9%fp4
Host 71$0.10$0.601.0M——100.0%unknown
Host 72$0.10$0.601.0M——100.0%fp8
Host 77maker's API$0.15$0.601.0M——100.0%unknown
Host 81$0.22$0.601.0M——98.9%unknown
Host 44$0.18$0.721.0M——100.0%fp8
Host 79$0.20$0.781.0M——100.0%fp8
Host 70$0.08$0.801.0M——99.6%unknown
Host 80$0.21$0.841.0M——100.0%unknown
Host 39$0.23$0.901.0M——100.0%unknown
Host 47$0.24$0.961.0M——100.0%fp8
Host 66$0.02$1.001.0M——100.0%fp4
Host 82$0.25$1.001.0M——100.0%unknown
Host 83$0.28$1.131.0M——100.0%fp8
Host 78$0.15$1.201.0M——100.0%fp8
Host 84$0.29$1.201.0M——99.9%fp8
Host 85$0.30$1.201.0M——98.9%fp8
Host 86$0.30$1.201.0M——99.9%unknown
Host 43$0.30$1.201.0M——99.1%fp8
Host 63$0.30$1.201.0M——100.0%unknown
Host 87$0.30$1.201.0M——100.0%unknown
Host 88$0.30$1.201.0M——100.0%unknown
Host 89$0.30$1.201.0M——100.0%unknown
Host 29$0.30$1.201.0M——99.9%fp8
Host 90$0.33$1.321.0M——98.9%unknown
Anonymised third-party hosts. Sorted by lowest output price. Speed and time to first token are medians from our nightly probe where measured; uptime is the catalog's 24-hour figure.

Compare with...