35% offprompt cache

Kimi K2.8 Preview

kimi-k2.8-preview

Kimi K2.8 Preview — 1M token context, up to 32,000 output tokens, text / image input, prompt caching.

Try in playground Get an API key

Input / output per 1M

$0.617/$2.60

official $0.95 / $4

Network fee$0.0010

ProviderMoonshot

ModalityText, Image

Context

Max output

32K

Input / 1M

$0.617

Output / 1M

$2.60

Pricing

Input / 1M$0.617$0.95

Output / 1M$2.60$4

Network fee$0.0010per request

35% below the official upstream price.

Request

POST /v1/chat/completions

curl https://api.relayrouter.org/v1/chat/completions \
  -H "Authorization: Bearer $RELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.8-preview",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'