PipeLLM logo
Back to approved models

Approved model profile_

DeepSeekactive

DeepSeek V3.2

DeepSeek V3.2 is a reasoning-oriented DeepSeek model designed for efficient long-context processing, coding, and agentic tool-use workloads. It uses sparse-attention style optimizations to improve throughput while preserving strong performance on multi-step reasoning and software tasks.

deepseek-v3.2
Open Relay View integration
relay/request.mjsready to route
const completion = await client.chat.completions.create({
  model: "deepseek-v3.2",
  messages: [
    { role: "user",
      content: "Plan a multi-step task" }
  ]
});
policy checked provider selected
CONTEXT128K contextprompt window
MAX OUTPUT32Kper response
INPUT$3.0 / Mtoken price
OUTPUT$3.0 / Mtoken price

Route configuration_

Use the model through the contract you already have.

PipeLLM resolves provider access, policy, and supported model capabilities without changing the interface your application calls.

ENDPOINThttps://api.pipellm.ai/openaiOpenAI-compatible route
MODEL IDdeepseek-v3.2Use this in every request
GOVERNANCEPolicy controlledApprovals and tool rules apply
PROVIDER AVAILABILITY1 route
ProviderContextMax outputInput / MOutput / M
Volcengine128K context32K$3.0 / M$3.0 / M
Displayed pricing is per one million tokens and may vary by provider.
SUPPORTED SURFACESactive
input: textoutput: texttool use

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