NVIDIA NIM: DeepSeek V3.2 (NIM)

Name: DeepSeek V3.2 (NIM) API
Brand: Deepseek

stable

DeepSeek V3.2 (NIM) is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

deepseek-ai__deepseek-v3.2deepseek

Provider Quick start

Context

163.8K

tokens

Max output

65.5K

tokens

Input

per 1M

Output

per 1M

Activity

Daily period usage

Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M

Pricing

Item	Price	Unit
Input	-	per 1M tokens
Output	-	per 1M tokens

Performance

Reliability

Compare

Compare usage and performance

Place this model beside up to three other catalog models.

Capabilities

Modalities

Input

Output

Details

Model ID: deepseek-ai__deepseek-v3.2
Family: deepseek
Status: stable
Knowledge: -
Released: -

Gateway Config

API: 2024-01-01
Auth: NVIDIA_API_KEY
Discovery: static
Provider type: meta

Quick Start

index.ts

import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@nvidia-nim/deepseek-ai__deepseek-v3.2",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL

https://integrate.api.nvidia.com/v1

Chat completions

https://integrate.api.nvidia.com/v1/chat/completions

Model

deepseek-ai__deepseek-v3.2

Auth env

NVIDIA_API_KEY

DeepSeek V3.2 (NIM) FAQ

What is the context window of DeepSeek V3.2 (NIM)?

DeepSeek V3.2 (NIM) accepts up to 163.8K tokens of context and returns up to 65.5K output tokens on NVIDIA NIM.

Which providers offer DeepSeek V3.2 (NIM)?

DeepSeek V3.2 (NIM) is available from NVIDIA NIM and Fireworks AI. Everstack can route between them with automatic fallback when one is unavailable.

What can DeepSeek V3.2 (NIM) do?

DeepSeek V3.2 (NIM) supports chat, function calling and reasoning. It accepts text input.

How do I call DeepSeek V3.2 (NIM) through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @nvidia-nim/deepseek-ai__deepseek-v3.2. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.