Deepseek V4 Flash

Name: Deepseek V4 Flash
Brand: DeepSeek
SKU: deepseek-v4-flash

DeepSeek V4 Flash is an efficiency-focused Mixture-of-Experts model built for fast inference, high-throughput applications, coding assistants, chat systems, and agent workflows. It keeps strong reasoning and coding performance while prioritizing responsiveness and cost efficiency.

deepseek-v4-flash

Open Relay View integration

relay/request.mjsready to route

const completion = await client.chat.completions.create({
  model: "deepseek-v4-flash",
  messages: [
    { role: "user",
      content: "Plan a multi-step task" }
  ]
});

CONTEXT1M contextprompt window

MAX OUTPUT384Kper response

INPUT$0.15 / Mtoken price

OUTPUT$0.30 / Mtoken price

Route configuration_

Choose a supported call format.

Select a format below to view its documentation. Use the displayed converter route when calling through PipeLLM.

ENDPOINThttps://api.pipellm.aiOne base URL for OpenAI Chat Completions, Responses, Anthropic, and Gemini.

SUPPORTED CALL FORMATS

OpenAI/openai/v1/chat/completionsDocs Responses/responses/v1/responsesDocs Anthropic/anthropic/v1/messagesDocs Gemini/gemini/v1beta/models/{model}:generateContentDocs Choose a call format to open its request and response documentation.

MODEL IDdeepseek-v4-flashUse this in every request

GOVERNANCEPolicy controlledApprovals and tool rules apply

PROVIDER AVAILABILITY3 routes

Provider	Context	Max output	Discount	Input / M	Output / M
Alibaba	1M context	384K	—	$0.15 / M	$0.30 / M
Volcano Engine	1M context	384K	—	$0.15 / M	$0.30 / M
Deepinfra	100M context	16.4K	—	$0.10 / M	$0.20 / M

Displayed pricing is per one million tokens and may vary by provider.

SUPPORTED SURFACESactive

input: textoutput: texttool usecache control

Relay governs model access with the same routing policy that Lens keeps visible and auditable.