Moonshot v1 8K API

moonshot-v1-8k

Moonshot v1 8K is a language model from Moonshot, available through the GPUniq API under the identifier `moonshot-v1-8k`. Pricing starts at $0.20 per 1M input tokens. It is reachable from the OpenAI-compatible endpoint, so any client that speaks the OpenAI Chat Completions API works by changing two settings: the base URL and the key.

Try moonshot-v1-8k API documentation

Pricing

Every request is billed on two counters: the tokens you send (prompt, system message, conversation history, any attached images) and the tokens the model generates. Output is the pricier side on essentially every model, and reasoning tokens count as output even when you never see them. Prices below are per 1,000,000 tokens.

Billed for	GPUniq
Inputper 1M tokens	$0.20
Outputper 1M tokens	$2.00

Billed from your GPUniq balance as you use it — no subscription, no monthly minimum, no per-seat fee. Prices refresh from the live catalog hourly.

Specifications

What the model accepts, what it returns, and the limits you will hit first.

API identifier: moonshot-v1-8k
Pass this exact string as the "model" field of your request.
Type: Chat & text
Served by Moonshot.

Detailed specs are not published for this model. Everything above comes from the GPUniq catalog; we would rather show less than guess.

How to call it

Any OpenAI-compatible client works: change the base URL and the key, keep everything else.

Endpoint

POST /v1/openai/chat/completions

Base URL

https://api.gpuniq.com/v1/openai

curl https://api.gpuniq.com/v1/openai/chat/completions \
  -H "Authorization: Bearer YOUR_GPUNIQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshot-v1-8k",
    "messages": [{"role": "user", "content": "Explain rate limiting in one paragraph."}]
  }'

Create a key on /chat and send it as a bearer token. The same key works across every model in the catalog, so switching models means changing one string.

moonshot-v1-8k — frequently asked

How much does moonshot-v1-8k cost?

$0.20 per 1M input tokens and $2.00 per 1M output tokens on GPUniq. Billing is pay-as-you-go from your balance — no subscription and no monthly minimum.

How do I call moonshot-v1-8k from my code?

Point any OpenAI-compatible client at https://api.gpuniq.com/v1/openai, use a GPUniq API key as the bearer token, and pass "moonshot-v1-8k" as the model. The official OpenAI SDKs, LangChain, Cursor, Cline and OpenWebUI all work unmodified — only the base URL and the key change.