Last updated: Oct 14, 2026 59 sources 20 endpoints monitored

deepseek-v4-flash-0731

1435 Score third-party Elo · arena.ai / LMArena ?

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

LLM & Generative AI 1 model 5 listings snapshot Oct 14, 2026, 12:54 AM

Platforms

click a card to open the detail table

Model variants

W3r9 dedup — same model + identical tags merge; prices are listed per billing form
Model Provider Tags Input /1M Output /1M
deepseek/deepseek-v4-flash-0731 OpenRouter 1M contextreasoning $0.016 $0.640
deepseek-ai/DeepSeek-V4-Flash-0731 DeepInfra 1M contextreasoning $0.060 $0.180
deepseek-ai/DeepSeek-V4-Flash-0731 Together 1M context $0.140 $0.280
deepseek-v4-flash-0731 DashScope 1M contextreasoning $0.222 $0.667
deepseek/deepseek-v4-flash-0731 Novita 1M contextreasoning $0.440 $1.32

Capabilities

official design_arena & architecture metadata

Design Arena Elo official design_arena benchmark (OpenRouter)

  • website 1240 · 46.7% wr
  • uicomponent 1238 · 46.8% wr
  • codecategories 1232 · 46.4% wr
  • gamedev 1213 · 44.6% wr
  • 3d 1210 · 48.7% wr
  • svg 1185 · 45.1% wr
  • dataviz 1182 · 41.1% wr
  • asciiart 1093 · 33.3% wr

Input / Output modalities modality: text->text

  • text in+out

Platform details

per provider
provider model Input /1M Output /1M Latency ? Official $/1M Availability Data time
DashScope deepseek-v4-flash-0731 $0.222 $0.667 — — — 2026-10-14 00:53:13
DeepInfra deepseek-ai/DeepSeek-V4-Flash-0731 $0.060 $0.180 — — — 2026-10-14 00:43:44
Novita deepseek/deepseek-v4-flash-0731 $0.440 $1.32 — — — 2026-10-14 00:54:15
OpenRouter deepseek/deepseek-v4-flash-0731 $0.016 $0.640 128.1 ms — 100% available 2026-10-14 00:43:21
Together deepseek-ai/DeepSeek-V4-Flash-0731 $0.140 $0.280 — — — 2026-10-14 00:53:13

5 rows · snapshot 2026-10-14 00:54:15 · from data/public/prices.json + measurements.json