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

DeepSeek V4 Flash 0731 API

Open in consoleI need inference
  • 1.05MContext
  • 384KMax output
  • $0.06/ $0.18From, per 1M in / out
  • 4Providers
Providers
  • DeepInfra
  • Nebius
  • Inference.net
  • Sail Research

Pricing

ProviderInput / 1MCached / 1MOutput / 1M
DeepInfraDefaultLowest$0.06$0.015$0.18
Nebius$0.14$0.01$0.28
Inference.net$0.53$0.017$1.58
Sail Research$0.09$0.02$0.18

USD, as of October 27, 2026. Live prices

Cost

WorkloadDeepInfra
1,000 chat replies2K in, 500 out each$0.21
1,000 agent tasks50K in, 5K out each$3.90
Monthly batch job500M in, 50M out$39.00

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-flash-0731",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

FAQ

How much does the DeepSeek V4 Flash 0731 API cost?

On RouterPlus, DeepSeek V4 Flash 0731 costs $0.06 per million input tokens and $0.18 per million output tokens at DeepInfra, the lowest listed prices and the provider where routing starts. Prices as of October 27, 2026.

Which providers serve DeepSeek V4 Flash 0731?

4 providers serve DeepSeek V4 Flash 0731 on RouterPlus: DeepInfra, Nebius, Inference.net 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 Flash 0731 model ID?

Use "deepseek/deepseek-v4-flash-0731" 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 Flash 0731 context window?

1.05M tokens of context and up to 384K output tokens, per the RouterPlus catalog. A provider can list a lower limit; the console shows each one.

Is DeepSeek V4 Flash 0731 open weights?

Yes. DeepSeek publishes DeepSeek V4 Flash 0731 as an open-weight model, which is why several independent providers can host it.

Do any DeepSeek V4 Flash 0731 providers retain prompts?

None of the 4 providers serving DeepSeek V4 Flash 0731 on RouterPlus list prompt retention.

Can I reserve capacity for DeepSeek V4 Flash 0731?

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 Flash 0731 at volume?

Open in consoleI need inference