Skip to content
Dashboard

Kimi K3 Fast

Kimi K3 Fast is the faster serving path for Moonshot AI's Kimi K3. It trades a higher per-token rate for lower latency, keeps the context window of 1M tokens, and routes through AI Gateway via Fireworks, Morph, Wafer. Your use is subject to Moonshot AI's Terms & Privacy Policies.

ReasoningTool UseImplicit CachingFile InputVision (Image)
import { streamText } from 'ai'
const result = streamText({
model: 'moonshotai/kimi-k3-fast',
prompt: 'Why is the sky blue?'
})
Read docs

More models by Moonshot AI

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Release Date
1M
1.0s
106tps
$2.90/MFast $4.50/M
$14/MFast $22.50/M
Read:$0.29/M
Write:
+2
baseten logo
digitalocean logo
fireworks logo
+4
07/16/2026
262K
0.5s
165tps
$1.90/M
$8/M
Read:$0.38/M
Write:
+2
fireworks logo
moonshotai logo
06/15/2026
262K
0.2s
164tps
$0.74/MFast $1.90/M
$3.50/MFast $8/M
Read:$0.15/M
Write:
+2
baseten logo
deepinfra logo
fireworks logo
+1
06/12/2026
262K
0.3s
347tps
$0.95/M
$4/M
Read:$0.16/M
Write:
+1
baseten logo
fireworks logo
moonshotai logo
+2
04/20/2026
262K
0.4s
106tps
$0.60/M
$3/M
Read:$0.1/M
Write:
+1
bedrock logo
moonshotai logo
novita logo
01/26/2026
216K
0.5s
59tps
$0.47/M
$2/M
Read:$0.14/M
Write:
deepinfra logo
11/06/2025