Skip to content
Model Pareto

DeepSeek V4.1 Flash

DeepSeekOpen weightsapi-docs.deepseek.com ↗
Compare with nearest rivalsCompare with…
Input
$0.30/M tok
Output
$1.20/M tok
Blended
$0.525/M tok · 3:1
Speed
232tok/s
Context
1Mtokens

Open weights (MIT). Peak-hour price; off-peak is 50% off.

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.

Hardware
8× B200 180GB
FP8 weights
Throughput
~39,657 tok/s
many requests batched
Price
$0.14–1.22 /M tok
busy → light use
On your own machine
Mac Studio M5 Ultra 512GB (int4, ~110 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (552B params, 16B active per token) + 40% KV-cache headroom ≈ 773 GB
  • 8× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~39,657 output tok/s aggregate at batch 1135 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~531,563 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

SWE-bench VerifiedEstimated
~#3 of 14 (estimated)~83.2%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. ~#3DeepSeek V4.1 FlashEstimated83.2%
  4. #3Gemini 3.1 Pro80.6%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#5 of 20 (estimated)~88.7%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. #4Nemotron 3 Ultra89.0%
  4. ~#5DeepSeek V4.1 FlashEstimated88.7%
  5. #5gpt-oss-120b87.8%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~#10 of 15 (estimated)~48.0
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #9Kimi K351.9
  4. ~#10DeepSeek V4.1 FlashEstimated48.0
  5. #10Grok 4.647.0
No published score — estimated from related benchmarks

Writing & chat

IFBenchEstimated
~#19 of 126 (estimated)~75.5%
  1. #1MiniMax-M382.9%
  2. #2Qwen3.8 2.4T A95B82.8%
  3. #18Gemma 4 31B75.6%
  4. ~#19DeepSeek V4.1 FlashEstimated75.5%
  5. #19GPT-5.3 Codex75.4%
No published score — estimated from related benchmarks
MMMLUEstimated
~#2 of 5 (estimated)~90.8%
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2DeepSeek V4.1 FlashEstimated90.8%
  3. #2Gemma 4 31B88.4%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Verified
#12 of 531462 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #11GLM-5.3 Flash1463
  4. #12DeepSeek V4.1 Flash1462
  5. #13MiMo-V2.6-Pro1461
lmarena.ai · 2026-09-25
LMArena Text (Elo)Verified
#13 of 531477 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #10MiMo-V2.6-Pro1480
  4. #13DeepSeek V4.1 Flash1477
  5. #14GLM-5.3 Flash1475
lmarena.ai · 2026-09-25

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2DeepSeek V4.1 FlashEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~#5 of 9 (estimated)~79.2%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #4Qwen3.8-Omni-Flash83.5%
  4. ~#5DeepSeek V4.1 FlashEstimated79.2%
  5. #5Muse Glimmer78.8%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#5 of 8 (estimated)~85.2%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #4Gemini 3.1 Pro85.3%
  4. ~#5DeepSeek V4.1 FlashEstimated85.2%
  5. #5Claude Haiku 4.579.6%
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#2 of 25 (estimated)~96.7%
  1. #1Inkling97.1%
  2. ~#2DeepSeek V4.1 FlashEstimated96.7%
  3. #2Muse Glimmer94.7%
No published score — estimated from related benchmarks

Agents

OSWorld-VerifiedEstimated
~#5 of 12 (estimated)~81.7%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #4MiMo-V2.6-Pro82.0%
  4. ~#5DeepSeek V4.1 FlashEstimated81.7%
  5. #5Claude Sonnet 581.2%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~57.7%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3DeepSeek V4.1 FlashEstimated57.7%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#7 of 18 (estimated)~87.6%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #6Step 5 Preview88.7%
  4. ~#7DeepSeek V4.1 FlashEstimated87.6%
  5. #7GPT-5.6 Terra87.5%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#14 of 89 (estimated)~40.7%
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #13GPT-6 Astra41.4%
  4. ~#14DeepSeek V4.1 FlashEstimated40.7%
  5. #14GPT-5.6 Terra40.2%
No published score — estimated from related benchmarks