tokenstat
tokenstat
DeepSeek

DeepSeek: V4 Pro 0813

deepseek/deepseek-v4-pro-0813 · rates as of · How this catalog is built · Benchmarks

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

Cheapest input
$0.115
$/MTok · models.dev
Cheapest output
$4
$/MTok
Context
1.0M
tokens
Sources
3
54 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

Input $/MTok over sampled dates
Output $/MTok
  • ↑ higherOutput $1.90 → $4
  • ↓ lowerInput $0.6 → $0.115
  • ↑ higherOutput $0.6811 → $1.90
  • ↑ higherInput $0.227 → $0.6
  • ↑ higherOutput $0.4198 → $0.6811
  • ↑ higherInput $0.1399 → $0.227
  • ↑ higherOutput $0.396 → $0.4198
  • ↑ higherInput $0.132 → $0.1399

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (3 omitted). Show free/$0 listings.

SourceProviderInputOutputCache readContext
models.devcheapestdeepseek/deepseek-v4-pro-0813OpenRouter$0.115$4$0.111.0M
OpenRouterdeepseek/deepseek-v4-pro-0813OpenRouter$0.115$5.50$0.111.0M
models.devdeepseek-ai/DeepSeek-V4-Pro-0813RunInfra$0.6$1.90$0.031.0M
models.devdeepseek/deepseek-v4-pro-0813NanoGPT$0.66$1.98$0.0221.0M
models.devdeepseek/deepseek-v4-pro-0813OrcaRouter$0.66$1.98$0.0221M
models.devdeepseek/deepseek-v4-pro-0813Vercel AI Gateway$0.66$1.98$0.0661M
models.devdeepseek-v4-pro:0813Ollama Cloud$0.66$1.98$0.0221.0M
models.devtencent/deepseek-v4-pro-0813Eden AI$0.66$1.98$0.0221M
models.devdeepseek/deepseek-v4-pro-0813:thinkingNanoGPT$0.66$1.98$0.0221.0M
models.devdeepseek-v4-pro-0813AIHubMix$0.6918$2.08$0.02311M
models.devdeepseek/deepseek-v4-pro-0813IteraCompute$0.79$2.38$0.0261.0M
LiteLLMDeepSeek-V4-Pro-0813N/A$0.92$2.77$0.04N/A
LiteLLMdeepseek-ai/DeepSeek-V4-Pro-0813N/A$0.92$2.77$0.04N/A
LiteLLMsail/deepseek-ai/DeepSeek-V4-Pro-0813N/A$0.92$2.77$0.04N/A
models.devdeepseek-v4-pro-0813Boundless$1.04$2.08$0.03521.0M
models.devdeepseek/deepseek-v4-pro-0813Standard Compute$1.12$3.37$0.11221M
models.devdeepseek-ai/DeepSeek-V4-Pro-0813DeepInfra$1.30$2.60$0.11.0M
models.devdeepinfra/deepseek-ai/DeepSeek-V4-Pro-0813Eden AI$1.30$2.60$0.11.0M
models.devdeepseek-ai/DeepSeek-V4-Pro-0813CoreWeave$1.31$3.96$0.0441.0M
LiteLLMdatabricks-deepseek-v4-pro-0813N/A$1.32$3.96$0.132N/A
LiteLLMdatabricks/databricks-deepseek-v4-pro-0813N/A$1.32$3.96$0.132N/A
models.devdeepseek/deepseek-v4-pro-0813Arcee$1.32$3.96$0.0441.0M
models.devdeepseek/deepseek-v4-pro-0813Kilo Gateway$1.32$3.96$0.0441.0M
models.devdeepseek/deepseek-v4-pro-0813Novita AI$1.32$3.96$0.0441.0M
models.devdeepseek/deepseek-v4-pro-0813Ofox$1.32$3.96$0.0441M
models.devdeepseek-v4-pro-0813DigitalOcean$1.32$3.96$0.0441.0M
models.devdeepseek-v4-pro-0813EmpirioLabs AI$1.32$3.96$1.321M
models.devdeepseek-v4-pro-0813Requesty$1.32$3.96$0.0441M
models.devdeepseek-ai/DeepSeek-V4-Pro-0813Baseten$1.32$3.96$0.1321.0M
models.devdeepseek-ai/DeepSeek-V4-Pro-0813Hugging Face$1.32$3.96$01M
models.devdeepseek-ai/DeepSeek-V4-Pro-0813Nebius$1.32$3.96$0.04979K
models.devdeepseek-ai/DeepSeek-V4-Pro-0813SiliconFlow$1.32$3.96$0.0441M
models.devdeepseek-ai/DeepSeek-V4-Pro-0813Together AI$1.32$3.96$0.131.0M
models.dev@cf/deepseek-ai/deepseek-v4-pro-0813Cloudflare$1.32$3.96$0.0441.0M
models.devcloudflare/@cf/deepseek-ai/deepseek-v4-pro-0813Eden AI$1.32$3.96$0.0441.0M
models.devperplexity/deepseek-v4-pro-0813Perplexity$1.32$3.96$0.0441M
LiteLLMdeepseek/deepseek-v4-pro-0813N/A$1.32$3.96$0.132N/A
LiteLLMdeepseek-v4-pro-0813N/A$1.32$3.96$0.044N/A
LiteLLMtencent/deepseek-v4-pro-0813N/A$1.32$3.96$0.044N/A
LiteLLMperplexity/perplexity/deepseek-v4-pro-0813N/A$1.32$3.96$0.044N/A
LiteLLMaccounts/fireworks/models/deepseek-v4-pro-0813N/A$1.32$3.96$0.044N/A
LiteLLMfireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813N/A$1.32$3.96$0.044N/A
LiteLLMnovita/deepseek/deepseek-v4-pro-0813N/A$1.32$3.96$0.132N/A
LiteLLMstreamlake/DeepSeek-V4-Pro-0813N/A$1.32$3.96$0.044N/A
models.devdeepseek-v4-pro-0813Vivgrid$1.35$3$0.051M
models.devdeepseek-v4-pro-0813Charm Hyper$1.44$4.31$0.04791M
models.devdeepseek-v4-pro-0813Venice AI$1.65$4.95$0.1651M
LiteLLMinferenceapis/deepseek-ai/DeepSeek-V4-Pro-0813N/A$1.72$5.15$0.17N/A
models.devdeepseek/deepseek-v4-pro-0813Merge Gateway$1.74$3.48$0.00361M
models.devdeepseek-v4-pro-0813Bothub$1.77$5.30$01M
models.devdeepseek/deepseek-v4-pro-0813AI/ML API$1.84$3.68$0.15341.0M
models.devdeepseek-v4-pro-0813Cortecs$2$4$0.51.0M
models.devdeepseek/deepseek-v4-pro-0813TensorX$2$4$0.51.0M
models.devtensorx/deepseek/deepseek-v4-pro-0813Eden AI$2$4$0.51.0M

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Released: 2026-08-13Output limit: 944K tokensFamily: deepseek-thinking

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

See what this model costs you

The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.

macOSDownloadWindowsPreviewCLImacOS · Linux · WindowsApp StoreDownloadGoogle PlayDownload