NVIDIA NIM

NVIDIA NIM: Kimi K3 (NVIDIA NIM)

stable

Kimi K3 (NVIDIA NIM) is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

moonshotai__kimi-k3kimi-k3released Jul 16, 2026
ProviderQuick start
Context
1.0M
tokens
Max output
131.1K
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
NVIDIA NIM
NVIDIA NIM
1.0M--
Fireworks AI
Fireworks AI
1.0M$3.00$15.00
Hugging Face
Hugging Face
1M$3.00$15.00
Moonshot AI
Moonshot AI
1.0M$3.00$15.00
OpenRouter
OpenRouter
1.0M$3.00$15.00

Pricing

ItemPriceUnit
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

Capabilities
Modalities
Input
Output
Details
Model ID
moonshotai__kimi-k3
Family
kimi-k3
Status
stable
Knowledge
-
Released
Jul 16, 2026
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/moonshotai__kimi-k3",  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
moonshotai__kimi-k3
Auth env
NVIDIA_API_KEY

Kimi K3 (NVIDIA NIM) FAQ

What is the context window of Kimi K3 (NVIDIA NIM)?

Kimi K3 (NVIDIA NIM) accepts up to 1.0M tokens of context and returns up to 131.1K output tokens on NVIDIA NIM.

Which providers offer Kimi K3 (NVIDIA NIM)?

Kimi K3 (NVIDIA NIM) is available from NVIDIA NIM, Fireworks AI, Hugging Face, Moonshot AI and OpenRouter. Everstack can route between them with automatic fallback when one is unavailable.

What can Kimi K3 (NVIDIA NIM) do?

Kimi K3 (NVIDIA NIM) supports chat, function calling, image input and reasoning. It accepts text, image and video input.

How do I call Kimi K3 (NVIDIA NIM) through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @nvidia-nim/moonshotai__kimi-k3. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.