Skip to content
Model Pareto

DeepSeek V4.1 Flash

DeepSeekOpen weightsapi-docs.deepseek.com ↗
Input
$0.30/M tok
Output
$1.20/M tok
Blended
$0.525/M tok · 3:1
Speed
232tok/s
Context
1Mtokens
Cost per task
~$0.51/taskest.

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

Writing & chat

Vision

Hard reasoning

Agents

~#7 of 15 (estimated)~80.7%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #6MiMo-V2.6-Flash80.8%
  4. ~#7DeepSeek V4.1 FlashEstimated80.7%
  5. #7Muse Spark Open80.4%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~57.5%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3DeepSeek V4.1 FlashEstimated57.5%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#8 of 22 (estimated)~86.5%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #7GPT-5.6 Terra87.5%
  4. ~#8DeepSeek V4.1 FlashEstimated86.5%
  5. #8Gemini 3.1 Pro85.9%
No published score — estimated from related benchmarks
~#15 of 91 (estimated)~40.1%
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #14GPT-5.6 Terra40.2%
  4. ~#15DeepSeek V4.1 FlashEstimated40.1%
  5. #15DeepSeek V4 Pro (0813)39.6%
No published score — estimated from related benchmarks