Code Open Weight Modified MIT

Kimi K2.7 Code

by Moonshot AI

Prices last updated October 4, 2026

Coding-focused agentic model built on Kimi K2.6 with ~30% lower thinking-token usage. 1T MoE (32B active), native INT4 quantization, 256K context, text/image/video input. Forces thinking and preserve_thinking modes; tuned for long-horizon software engineering and agent workflows.

Parameters
1T MoE (32B active)
Context
262k
Providers
17
Cheapest Input
$0.671
Fastest
231.26 t/s
Vision Function Calling JSON Mode Streaming Chat / InstructCodeReasoningVision

Price Comparison

Compare pricing across 17 providers serving Kimi K2.7 Code

Provider Input $/1M Output $/1M Context Speed TTFT Status
OP
OpenRouter
$0.671 ● $3.35 262k — — Live
DE
DeepInfra
$0.680 $3.40 262k — — Live
WA
WaveSpeed AI
$0.710 $3.50 262k — — Live
PA
Parasail
$0.750 $3.50 262k — — Down
VE
Venice AI
$0.750 $3.50 256k — — Live
SI
SiliconFlow
$0.859 $3.80 262k — — Live
NO
Novita AI
$0.950 $4.00 — — — Live
FI
Fireworks AI
$0.950 $4.00 — — — Down
NE
NeuralWatt
$0.950 $4.00 262k — — Live
MO
Moonshot AI
$0.950 $4.00 262k — — Live
TO
Together AI
$0.950 $4.00 262k — — Down
CL
Cloudflare Workers AI
$0.950 $4.00 262k — — Live
NE
Nebius
$0.950 $4.00 262k 231.26 t/s ● — Live
AL
Alibaba Cloud
$0.950 $4.00 — — — Live
AT
Atlas Cloud
$0.950 $4.00 262k — — Live
AI
AIMLAPI
$1.24 $5.20 262k — — Live
MO
Moonshot AI HighSpeed
$1.90 $8.00 262k — — Live
● Cheapest ● Fastest Prices in USD per 1M tokens

Subscribe to our newsletter

News and updates, 1–2 emails per month. No spam.