Moonshot AI

Moonshot AI: Moonshot V1 8K

deprecated

Moonshot V1 8K is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

moonshot-v1-8kmoonshot-v1
Context
8.2K
tokens
Max output
4.1K
tokens
Input
$0.20
per 1M
Output
$2.00
per 1M

Activity

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

Providers

ProviderContextInput /MOutput /M

Pricing

ItemPriceUnit
Input$0.20per 1M tokens
Output$2.00per 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
moonshot-v1-8k
Family
moonshot-v1
Status
deprecated
Knowledge
-
Released
-
Gateway Config
API
v1
Auth
MOONSHOT_API_KEY
Discovery
static
Provider type
static

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: "@moonshot/moonshot-v1-8k",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL
https://api.moonshot.ai/v1
Chat completions
https://api.moonshot.ai/v1/chat/completions
Model
moonshot-v1-8k
Auth env
MOONSHOT_API_KEY

Moonshot V1 8K FAQ

How much does the Moonshot V1 8K API cost?

Through Moonshot AI, Moonshot V1 8K costs $0.20 per 1M input tokens and $2.00 per 1M output tokens.

What is the context window of Moonshot V1 8K?

Moonshot V1 8K accepts up to 8.2K tokens of context and returns up to 4.1K output tokens on Moonshot AI.

What can Moonshot V1 8K do?

Moonshot V1 8K supports chat and function calling. It accepts text input.

How do I call Moonshot V1 8K through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @moonshot/moonshot-v1-8k. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.