Kimi K2.7 Code HighSpeed pricing & specs

Moonshot AI · released 2026-06-12 · ● verified 2026-10-11

input / 1M$1.90
output / 1M$8.00
context262.1K
max output262.1K

// price history ($/1M tokens)

$9.20
input $/1Moutput $/1M2026-06-12 → 2026-10-11

// cheaper or similar alternatives

modelinoutctxvs Kimi K2.7 Code HighSpeed
Gemma 4 E2B IT$0.04$0.08131.1K−98.5%
Qwen3.7 Flash$0.03$0.131M−98.4%
Qwen3.5 9B$0.10$0.15262.1K−96.7%
Qwen3.5 Flash$0.10$0.401M−94.9%
Gemini 2.5 Flash-Lite$0.10$0.401.05M−94.9%
Grok 4.6 vs Kimi K2.7 Code HighSpeed →Grok 4.7 vs Kimi K2.7 Code HighSpeed →

// price by host

hostin $/1Mout $/1M
DeepInfra$0.68$3.40
Azure$0.95$4.00
Baseten$0.95$4.00
Cloudflare Workers AI$0.95$4.00
Nebius$0.95$4.00
Novita AI$0.95$4.00

// faq

How much does Kimi K2.7 Code HighSpeed cost?

Kimi K2.7 Code HighSpeed costs $1.90 per million input tokens and $8.00 per million output tokens. At 50M input and 10M output tokens per month that is about $175.

What is the context window of Kimi K2.7 Code HighSpeed?

262.1K tokens, with up to 262.1K output tokens per request.

Does Kimi K2.7 Code HighSpeed support prompt caching?

Yes. Cached input tokens cost $0.38 per million.

What are cheaper alternatives to Kimi K2.7 Code HighSpeed?

Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out), Qwen3.5 9B ($0.10 in / $0.15 out) offer the same input types and capabilities for less.

Is Kimi K2.7 Code HighSpeed open weights?

Yes. It is available from 6 tracked hosts; the cheapest is DeepInfra at $0.68 input and $3.40 output per million tokens.

// spec sheet

input / 1M
$1.90
output / 1M
$8.00
cache read / 1M
$0.38
blended (3:1)
$3.425
context
262.1K
max output
262.1K
input types
text · image · video
reasoning
yes
tool calling
yes
structured output
yes
open weights
yes
knowledge cutoff
2025-01
price source
Moonshot AI

report a data error

// cost calculator

modelin $/1Mout $/1M= monthly
Gemma 4 E2B IT$0.04$0.08$2.80
Qwen3.7 Flash$0.03$0.13$2.80
Qwen3.5 9B$0.10$0.15$6.50
Kimi K2.7 Code HighSpeed$1.90$8.00$175

Base-tier list prices. Long-context tiers, caching and batch discounts are not included.