Skip to content

DeepSeek V4.1 Flash 1017

DeepSeekOpen weightsReasoningVerifiedReleased Oct 17, 2026Input: text, image
Compare with Claude Opus 4.7Source scores ↗OpenRouter ↗
Overall score
65.7
Rank 35 of 222 · 60.7–70.7
Context window
1M
1,000,000 tokens
Price per 1M tokens
$0.15 in · $0.60 out
✓ Verified on DeepSeek's pricing page
Blended price
$0.26
3:1 input:output tokens
Output speed
—
Not measured yet

Category scores

Scores per capability area with the model's rank among ranked models in that category.

  1. 1Reasoning82.5
  2. 2Multimodal77.9
  3. 3Math70.1
  4. 4Knowledge69.7
  5. 5Coding#1862.9
Higher is better. #N is the model's rank in that category, where it is eligible to be ranked.

Benchmark results (30)

As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.

Agentic & tool use

Terminal-Bench 2.190.6#3 of 68
HLE w/ tools63.9#4 of 27
CyberGym88.1#3 of 25
AutomationBench60.5#2 of 25
Terminal-Bench 4.042.30#10 of 18
Agents' Last Exam35.4#7 of 17
ExploitGym15.3#7 of 14
CWE-bench v155.0#7 of 11

Coding

DeepSWE77.0#4 of 50
NL2Repo68.2#1 of 31
Bug Hunt Bench39.1#9 of 23
ProgramBench29.1#11 of 15
OpenHarmony Bench60.3#3 of 12
Codeforces3471.0#1 of 4

Multimodal

Design Arena Website1323#6 of 91
ParseBench65.72#21 of 37
ExtractBench (LlamaIndex)(lower is better)87.11#12 of 24
Chartography (tools)83.0#3 of 5
BabyVision w/ Python92.5#1 of 5
ZeroBench w/ Python51.0#1 of 3

Math

FrontierMath v2 (Tiers 1-3)67.368#27 of 64
FrontierMath v2 (Tier 4)26.829#30 of 51
Apex65.6#2 of 8

Knowledge

GPQA90.9#21 of 117
HLE42.6#27 of 69

Reasoning

STEMBench2.49#7 of 9

Pricing by source

USD per 1M tokens.

SourceInputOutputCached in
✓ Official (DeepSeek)
checked Oct 17, 2026 · deepseek-flash
$0.15$0.60$0.003
BenchLM list price$0.15$0.60$0.003
OpenRouter deepseek/deepseek-v4.1-flash$0.028$0.12$0.001

Off-peak price; peak hours (01:00-04:00 and 06:00-10:00 UTC, weekdays) cost 2x.

BenchLM/list lists input at $0.30; BenchLM/list lists output at $1.20; OpenRouter lists input at $0.028; OpenRouter lists output at $0.12, which differs from the official price.

DeepSeek's pricing page read October 17, 2026 lists `deepseek-flash` with model version DeepSeek-V4.1-Flash-1017 at the same peak and off-peak rates, and DeepSeek's October 17, 2026 changelog says the upgrade leaves the API calling method and pricing unchanged (https://api-docs.deepseek.com/updates). DeepSeek's pricing page checked September 10, 2026 lists `deepseek-flash` (model version DeepSeek-V4.1-Flash) with peak and off-peak rates, effective 04:00 UTC on September 10, 2026. The stored values are the peak rates: $0.30 cache-miss input / $0.006 cache-hit input / $1.20 output per million tokens. Off-peak rates are half of peak: $0.15 / $0.003 / $0.60. Peak hours are 01:00-04:00 and 06:00-10:00 UTC, Monday through Friday; all other hours are off-peak. The page lists a 1M context length, a 384K maximum output, and a 2,500-request concurrency limit. The legacy `deepseek-v4-flash` and `deepseek-v4-flash-vision-exp` IDs route to this model at the same Flash price, and DeepSeek's September 10, 2026 announcement said `deepseek-v4-pro` requests would join them from 04:00 UTC on September 14, 2026. DeepSeek's pricing page, read September 17, 2026, says V4 Pro API service continues after September 14, 2026 with the billing method unchanged, and that DeepSeek will give notice of any change; the September 10 post had not been edited when read the same day (https://api-docs.deepseek.com/news/news260910, https://api-docs.deepseek.com/quick_start/pricing). MIT-licensed weights are also published on Hugging Face for self-hosting.

Price history

  • Oct 17, 2026: $0.30 / $1.20
  • Oct 17, 2026: $0.15 / $0.60

Arena ratings

Human-preference ratings from LMArena. Best-rated variant shown.

Text(max)1463#38 · 12.8K votes

Open weights

From the Hugging Face repository.

Parameters
763B
Licence
mit
Downloads (30 days)
27.7K

Speed

Measured by us through OpenRouter (median of trials).

Not measured yet.

Related models

Similar score