Skip to content
NewTry RouterPlus with free creditsTry playground →
RouterPlus
Book a demo

DeepSeek V4 Pro 0813 API

Open in consoleI need inference
  • 1.05MContext
  • 524KMax output
  • $0.92/ $2.60From, per 1M in / out
  • 4Providers
Providers
  • DeepInfra
  • Nebius
  • Novita AI
  • Sail Research

Pricing

ProviderInput / 1MCached / 1MOutput / 1M
DeepInfraDefaultLowest output$1.30$0.10$2.60
Nebius$1.32$0.04$3.96
Novita AI$1.32$0.044$3.96
Sail ResearchLowest input$0.92$0.04$2.77

USD, as of October 27, 2026. Live prices

Cost

WorkloadDeepInfraSail Research
1,000 chat replies2K in, 500 out each$3.90$3.23
1,000 agent tasks50K in, 5K out each$78.00$59.85
Monthly batch job500M in, 50M out$780.00$598.50

Quickstart

OpenAI-compatible
curl https://api.routerplus.com/v1/chat/completions \
  -H "Authorization: Bearer $ROUTERPLUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-pro-0813",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

FAQ

How much does the DeepSeek V4 Pro 0813 API cost?

On RouterPlus, routing for DeepSeek V4 Pro 0813 starts at DeepInfra: $1.30 per million input tokens and $2.60 per million output tokens. The lowest listed input price is $0.92 at Sail Research, and the lowest listed output price is $2.60 at DeepInfra. Name a provider with provider.only and you pay its price. Prices as of October 27, 2026.

Which providers serve DeepSeek V4 Pro 0813?

4 providers serve DeepSeek V4 Pro 0813 on RouterPlus: DeepInfra, Nebius, Novita AI and Sail Research. By default the router tries them in routing order and fails over before the first byte, never mid-answer.

What is the DeepSeek V4 Pro 0813 model ID?

Use "deepseek/deepseek-v4-pro-0813" as the model with the OpenAI-compatible endpoint at https://api.routerplus.com/v1. The same key also accepts the Anthropic API format.

What is the DeepSeek V4 Pro 0813 context window?

1.05M tokens of context and up to 524K output tokens, per the RouterPlus catalog. A provider can list a lower limit; the console shows each one.

Is DeepSeek V4 Pro 0813 open weights?

Yes. DeepSeek publishes DeepSeek V4 Pro 0813 as an open-weight model, which is why several independent providers can host it.

Do any DeepSeek V4 Pro 0813 providers retain prompts?

None of the 4 providers serving DeepSeek V4 Pro 0813 on RouterPlus list prompt retention.

Can I reserve capacity for DeepSeek V4 Pro 0813?

Yes. Tell us the model, the throughput you need and the region with "I need inference", and RouterPlus lines up reserved capacity for it.

More DeepSeek

All DeepSeek modelsAll models

Need DeepSeek V4 Pro 0813 at volume?

Open in consoleI need inference