DeepSeek

DeepSeek: DeepSeek V4 Flash 0423

deepseek/deepseek-v4-flash-20260423Hugging Face ↗

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

toolsstructuredreasoning
Data source

DeepSeek: DeepSeek V4 Flash 0423 usage over time

OpenRouter share of tokens, by day.

View
Tidelines — LLM usage and market share

DeepSeek: DeepSeek V4 Flash 0423 holds 1.94% today, up from 0.83% at the start of the visible window.

Data: OpenRouter as of 2026-10-08 · Source: tidelines.ai/models/deepseek-deepseek-v4-flash-20260423

Rank history

Tidelines — LLM usage and market share
Data: OpenRouter as of 2026-10-08 · Source: tidelines.ai/models/deepseek-deepseek-v4-flash-20260423

Adoption curve vs the pantheon

DeepSeek: DeepSeek V4 Flash 0423'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 2026-10-08 · Source: tidelines.ai/models/deepseek-deepseek-v4-flash-20260423

Citable stat

As of 2026-10-08, DeepSeek: DeepSeek V4 Flash 0423 holds 1.9% of OpenRouter token share, down 1.60pp over 30 days. Source: Tidelines (OpenRouter).

Cost per session

Median dollars spent on one DeepSeek: DeepSeek V4 Flash 0423 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$0.0013$0.0050$0.036$0.340
Kilo Code$0.0003$0.0052$0.031$0.265
Hermes Agent$0.0011$0.0040$0.028$0.190
Codex$0.0005$0.0021$0.014$0.020

Compare every model's session cost →

Data: OpenRouter session-cost dataset as of 2026-09-27 · Source: tidelines.ai/models/deepseek-deepseek-v4-flash-20260423

Where to run it

DeepSeek: DeepSeek V4 Flash 0423 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 0423 is served by 16 tracked endpoints on OpenRouter. The cheapest output price is $0.17 per million tokens from StreamLake, and the most expensive is $1.32 from Cloudflare. The largest context window offered is 1049k tokens. Prices are list rates and refresh daily.

ProviderInput $/MOutput $/MContextUptime
StreamLake$0.08$0.171024k100.00%
Wafer$0.40$0.171049k100.00%
DeepInfra$0.09$0.181049k100.00%
GMICloud$0.09$0.181049k100.00%
Venice$0.10$0.191000k100.00%
DigitalOcean$0.10$0.201049k100.00%
SiliconFlow$0.13$0.281049k100.00%
Baidu$0.14$0.281049k100.00%
AtlasCloud$0.14$0.281049k50.00%
Parasail$0.14$0.281049k100.00%
Alibaba$0.15$0.301000k100.00%
Mancer 2$0.19$0.501049k86.67%
Azure$0.21$0.561049k100.00%
OpenInference$0.04$1.151049k100.00%
Relace$0.05$1.281049k100.00%
Cloudflare$0.44$1.32384k100.00%