kimi-latest-30%
kimi-latestMoonshot Kimi open-weights MoE model with strong agentic and multilingual performance.
CONTEXT
128K
RELEASED
—
INPUT /MTOK
$1.4$2
OUTPUT /MTOK
$3.5$5
Connect
Call kimi-latest through the gateway. Native is the model's own wire protocol; Compatible endpoints are translated by the gateway.
POST /v1/responsesNativecurl https://apiarc.ai/v1/responses \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $APIARC_API_KEY" \
-d '{
"model": "kimi-latest",
"input": "Hello"
}'Providers
Routes offering kimi-latest through the gateway, with list pricing.
| Provider | Input /M | Output /M | Cache read /M | Latency (30d avg) |
|---|---|---|---|---|
Moonshot Kimi-30% | $1.4$2 | $3.5$5 | $0.105$0.15 | — |