DeepSeek

DeepSeek: DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-20260731Hugging Face ↗

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....

toolsstructuredreasoning
Data source

DeepSeek: DeepSeek V4 Flash 0731 usage over time

OpenRouter share of tokens, by day.

View
Tidelines — LLM usage and market share

DeepSeek: DeepSeek V4 Flash 0731 holds 8.49% today, up from 1.41% at the start of the visible window.

Data: OpenRouter as of 2026-09-15 · Source: tidelines.ai/models/deepseek-deepseek-v4-flash-20260731

Rank history

Tidelines — LLM usage and market share
Data: OpenRouter as of 2026-09-15 · Source: tidelines.ai/models/deepseek-deepseek-v4-flash-20260731

Adoption curve vs the pantheon

DeepSeek: DeepSeek V4 Flash 0731's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?

Tidelines — LLM usage and market share
Data: OpenRouter as of 2026-09-15 · Source: tidelines.ai/models/deepseek-deepseek-v4-flash-20260731

Citable stat

As of 2026-09-15, DeepSeek: DeepSeek V4 Flash 0731 holds 8.5% of OpenRouter token share, down 5.54pp over 30 days. Source: Tidelines (OpenRouter).

Cost per session

Median dollars spent on one DeepSeek: DeepSeek V4 Flash 0731 session, by coding agent and session length.

Tidelines — LLM usage and market share

Token rate sets the price; session length and reasoning set the bill.

Agent1 turn2–9 turns10–49 turns50+ turns
Claude Code$0.0018$0.0054$0.042$0.409
Hermes Agent$0.0013$0.0041$0.031$0.214
Kilo Code$0.0004$0.0052$0.030$0.286
Codex$0.0006$0.0024$0.016$0.024

Compare every model's session cost →

Data: OpenRouter session-cost dataset as of 2026-09-13 · Source: tidelines.ai/models/deepseek-deepseek-v4-flash-20260731

Where to run it

DeepSeek: DeepSeek V4 Flash 0731 pricing by provider

Tidelines — LLM usage and market share

Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.

DeepSeek: DeepSeek V4 Flash 0731 is served by 27 tracked endpoints on OpenRouter. The cheapest output price is $0.10 per million tokens from OpenInference, and the most expensive is $1.32 from Cloudflare. The largest context window offered is 1311k tokens. Prices are list rates and refresh daily.

ProviderInput $/MOutput $/MContextUptime
OpenInference$0.04$0.101049k99.99%
Relace$0.06$0.121049k97.79%
StreamLake$0.06$0.171024k97.16%
Inceptron$0.05$0.171049k98.50%
DeepInfra$0.06$0.181049k99.58%
Makora$0.09$0.201000k99.60%
DigitalOcean$0.12$0.241049k99.97%
Wafer$0.10$0.251049k99.94%
BaseTen$0.13$0.261049k100.00%
CoreWeave$0.13$0.28262k99.99%
Together$0.14$0.281049k99.96%
Parasail$0.14$0.281049k99.84%
Sail Research$0.07$0.341049k97.24%
Venice$0.17$0.351000k99.05%
Morph$0.14$0.401049k100.00%
Mancer 2$0.20$0.601049k99.19%
Reka$0.11$0.66262k99.96%
Fireworks$0.22$0.661049k88.26%
SiliconFlow$0.22$0.661049k99.66%
GMICloud$0.29$0.861049k100.00%
Phala$0.31$0.921049k99.91%
NextBit$0.35$1.061049k99.97%
Alibaba$0.35$1.061000k100.00%
Novita$0.41$1.231049k100.00%
Baidu$0.44$1.321049k100.00%
AtlasCloud$0.44$1.321049k100.00%
Cloudflare$0.44$1.321311k99.93%