Skip to content
Dashboard

Kimi K2 Thinking

Kimi K2 Thinking adds extended chain-of-thought (CoT) reasoning to the K2 architecture, supporting many sequential tool calls for agentic workflows through AI Gateway. Your use subject to Moonshot AI's Terms & Privacy Policies.

ReasoningTool UseImplicit Caching
index.ts
import { streamText } from 'ai'
const result = streamText({
model: 'moonshotai/kimi-k2-thinking',
prompt: 'Why is the sky blue?'
})

More models by Moonshot AI

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Release Date
1M
0.9s
106tps
$4.50/M
$22.50/M
Read:$0.45/M
Write:
+2
fireworks logo
morph logo
07/27/2026
1M
0.9s
100tps
$2.90/M
$14/M
Read:$0.29/M
Write:
+2
baseten logo
fireworks logo
moonshotai logo
+3
07/16/2026
262K
1.0s
218tps
$1.90/M
$8/M
Read:$0.38/M
Write:
+2
fireworks logo
moonshotai logo
06/15/2026
262K
0.3s
136tps
$0.74/M
$3.50/M
Read:$0.15/M
Write:
+2
baseten logo
deepinfra logo
fireworks logo
+1
06/12/2026
262K
0.3s
349tps
$0.95/M
$4/M
Read:$0.16/M
Write:
+1
baseten logo
fireworks logo
moonshotai logo
+2
04/20/2026
262K
0.5s
85tps
$0.60/M
$3/M
Read:$0.1/M
Write:
+1
bedrock logo
moonshotai logo
novita logo
01/26/2026