Fireworks AI: Kimi K3 (Fireworks)

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: "@fireworks/accounts__fireworks__models__kimi-k3",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL

https://api.fireworks.ai/inference/v1

Chat completions

https://api.fireworks.ai/inference/v1/chat/completions

Model

accounts__fireworks__models__kimi-k3

Auth env

FIREWORKS_API_KEY

Kimi K3 (Fireworks) FAQ

How much does the Kimi K3 (Fireworks) API cost?

Through Fireworks AI, Kimi K3 (Fireworks) costs $3.00 per 1M input tokens and $15.00 per 1M output tokens.

What is the context window of Kimi K3 (Fireworks)?

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

Which providers offer Kimi K3 (Fireworks)?

Kimi K3 (Fireworks) 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 (Fireworks) do?

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

How do I call Kimi K3 (Fireworks) through Everstack?

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

Activity

Providers

Pricing

Performance

Reliability

Compare

Capabilities

Quick Start