DeepSeek

DeepSeek: DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-20260813Hugging Face ↗

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

toolsstructuredreasoning
Data source

DeepSeek: DeepSeek V4 Pro 0813 usage over time

OpenRouter share of tokens, by day.

View
Tidelines — LLM usage and market share

DeepSeek: DeepSeek V4 Pro 0813 holds 1.02% today, down from 1.28% at the start of the visible window.

Data: OpenRouter as of 2026-09-01 · Source: tidelines.ai/models/deepseek-deepseek-v4-pro-20260813

Rank history

Tidelines — LLM usage and market share
Data: OpenRouter as of 2026-09-01 · Source: tidelines.ai/models/deepseek-deepseek-v4-pro-20260813

Adoption curve vs the pantheon

DeepSeek: DeepSeek V4 Pro 0813'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 2026-09-01 · Source: tidelines.ai/models/deepseek-deepseek-v4-pro-20260813

Citable stat

As of 2026-09-01, DeepSeek: DeepSeek V4 Pro 0813 holds 1.0% of OpenRouter token share, down 0.26pp over 30 days. Source: Tidelines (OpenRouter).

Cost per session

Median dollars spent on one DeepSeek: DeepSeek V4 Pro 0813 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$0.026$0.061$0.386$2.76
Hermes Agent$0.014$0.039$0.282$1.76
Kilo Code$0.0058$0.049$0.274$1.68

Compare every model's session cost →

Data: OpenRouter session-cost dataset as of 2026-08-30 · Source: tidelines.ai/models/deepseek-deepseek-v4-pro-20260813

Where to run it

DeepSeek: DeepSeek V4 Pro 0813 pricing by provider

Tidelines — LLM usage and market share

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

DeepSeek: DeepSeek V4 Pro 0813 is served by 17 tracked endpoints on OpenRouter. The cheapest output price is $2.60 per million tokens from DeepInfra, and the most expensive is $4.36 from Phala. The largest context window offered is 1049k tokens. Prices are list rates and refresh daily.

ProviderInput $/MOutput $/MContextUptime
DeepInfra$1.30$2.601049k99.63%
StreamLake$1.12$3.351024k99.99%
Alibaba$1.12$3.371000k99.98%
GMICloud$1.12$3.371049k99.84%
CoreWeave$1.31$3.961049k99.79%
NextBit$1.32$3.961049k99.55%
Sail Research$1.32$3.961049k100.00%
BaseTen$1.32$3.961049k100.00%
Parasail$1.32$3.961049k98.95%
Together$1.32$3.961049k99.23%
DigitalOcean$1.32$3.961049k100.00%
Novita$1.32$3.961049k100.00%
SiliconFlow$1.32$3.961049k100.00%
Cloudflare$1.32$3.961049k100.00%
Fireworks$1.32$3.961049k100.00%
DeepSeek$1.32$3.961049k99.99%
Phala$1.45$4.361049k100.00%