Fireworks AI: Kimi K3 Fast (Fireworks)

stable

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

accounts__fireworks__routers__kimi-k3-fastkimi-k3released Jul 27, 2026

Provider Quick start

Context

1.0M

tokens

Max output

131.1K

tokens

Input

$4.50

per 1M

Output

$22.50

per 1M

Activity

Daily period usage

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

Providers

ProviderContextInput /MOutput /M

Fireworks AI

1.0M$4.50$22.50

Pricing

Item	Price	Unit
Input	$4.50	per 1M tokens
Output	$22.50	per 1M tokens
Cache read	$0.45	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: accounts__fireworks__routers__kimi-k3-fast
Family: kimi-k3
Status: stable
Knowledge: -
Released: Jul 27, 2026

Gateway Config

API: 2024-01-01
Auth: FIREWORKS_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: "@fireworks/accounts__fireworks__routers__kimi-k3-fast",  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__routers__kimi-k3-fast

Auth env

FIREWORKS_API_KEY

Kimi K3 Fast (Fireworks) FAQ

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

Through Fireworks AI, Kimi K3 Fast (Fireworks) costs $4.50 per 1M input tokens and $22.50 per 1M output tokens.

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

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

What can Kimi K3 Fast (Fireworks) do?

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

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

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