Advertise here
#73

DeepSeek V4.1 Flash

DeepSeek Release: 2026-09-10 Tested on: 2026-10-01 04:39 deepseek/deepseek-v4.1-flash::max
748B total (16B active)MoEOpen source
(max) (high) (medium) (low) (none)

Summary

DeepSeek V4.1 Flash scores 8.6 on AI BENCHY and ranks #73. It has 9.4 reliability, a 69.6% pass rate, $1.204 total cost, and 61.58s average response time.

What makes DeepSeek V4.1 Flash unique: It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.

Model facts

Researched on 2026-09-10

Reported
Parameters
748B total (16B active)
Architecture
MoE
Availability
Open source
License
MIT

Total is 552B backbone plus 196B Engram conditional-memory parameters. Active count is 16B during decode; prefill activates 8B per token. The exact checkpoint includes MIT-licensed weights and a runnable inference implementation.

Parameter source Availability source

Score

8.6

Consistency

9.3

Reliability

9.4

Total Cost (Current Price)

$1.204 ↑ +116.1%

Tested at: $0.558

Total Output Tokens

908,171

Total Input Tokens

414,054

Input Price

$0.013 / 1M

Output Price

$1.320 / 1M

Cache Read Price

$0.013 / 1M

Cache Write Price

N/A

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 8

Attempt pass rate: 69.6%

Flaky tests

2

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

61.58s

Response Time (max): 335.08s

Response Time (total): 1416.24s

Wrong answer: 6 API error: 1 Did not follow instructions: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#73 DeepSeek V4.1 Flash

max
Cost
$0.066
Time
211.0s
Tokens
54,712 tok

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price Cache Read Price Cache Write Price
2026-10-06 14:54 $0.013 / 1M $1.320 / 1M $0.013 / 1M N/A

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

DeepSeek V4.1 FlashmaxvsGPT-6 SollowDeepSeek V4.1 FlashmaxvsMuse Spark 1.1lowDeepSeek V4.1 FlashmaxvsSeed 2.1 TurbomediumDeepSeek V4.1 FlashmaxvsClaude Sonnet 5.5highDeepSeek V4.1 FlashmaxvsMiMo-V2.6-PromediumDeepSeek V4.1 FlashmaxvsClaude Haiku 5.5lowDeepSeek V4.1 FlashmaxvsQwen3.8 27BhighFree AvailableDeepSeek V4.1 FlashmaxvsQwen3.8 Max (0902)lowDeepSeek V4.1 FlashmaxvsGPT-5.2mediumDeepSeek V4.1 FlashmaxvsGrok 4.6high

Category Breakdown

Category Score Consistency Tests Correct
Agentic 10.0 10.0
Anti-AI Tricks 8.3 10.0
Coding 10.0 10.0
Combined 10.0 10.0
Data parsing and extraction 6.5 10.0
Domain specific 3.6 7.2
General Intelligence 10.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 5.5 7.1
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models