Skip to content
RelayRouter
Model catalog
35% offprompt cache

Kimi K3

kimi-k3

Kimi K3 — 1.04858M token context, up to 1,048,576 output tokens, text / image input, prompt caching.

Try in playgroundGet an API key

Input / output per 1M

$1.95/$9.75

official $3 / $15

Network fee$0.0010
ProviderMoonshot
ModalityText, Image

Context

1.0M

Max output

1.0M

Input / 1M

$1.95

Output / 1M

$9.75

Pricing

Input / 1M$1.95$3
Output / 1M$9.75$15
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-k3",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'