moonshotaiListed Jun 11, 2026

MoonshotAI: Kimi K2.7 Code

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...

Context window262.1K
Max output235.9K
Provider endpoints18
Benchmark results0
Measured performance

Benchmark results

All leaderboards ↗
—

No published results in this index yet

Scores appear here when an evaluation matches this exact model.

Access & cost

Prices across providers

18 quotes

Your token mix

USD · listed token rates

ExperientialStandard list rate
$1.52
Inceptron · via OpenRouterinceptron/int4 · quantization=int4
$1.5087
CoreWeave · via OpenRoutercoreweave/int4 · quantization=int4
$1.585
Venice · via OpenRoutervenice/int4 · quantization=int4
$1.625
SiliconFlow · via OpenRoutersiliconflow/fp8 · quantization=fp8
$1.8092
Novita · via OpenRouternovita/int4 · quantization=int4
$1.872
Nebius · via OpenRouternebius/fp4 · quantization=fp4
$1.95
GMICloud · via OpenRoutergmicloud/fp8 · quantization=fp8
$1.95
Alibaba · via OpenRouteralibaba/fp8 · quantization=fp8
$1.95
Moonshot AI · via OpenRoutermoonshotai/int4 · quantization=int4
$1.95
Moonshot AI · via OpenRoutermoonshotai/highspeed · tier=priority · quantization=int4
$3.90

OpenRouter

Catalog quote
Input
$0.6712
Output
$3.35
Cached input
$0.18
USD / 1M tokens
262.1K context235.9K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/kimi-k2.7-code

novita

via Hugging Face
Input
$0.95
Output
$4.00
USD / 1M tokens
262.1K contextPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/Kimi-K2.7-Code

deepinfra

via Hugging Face
Input
$0.68
Output
$3.40
USD / 1M tokens
262.1K contextPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/Kimi-K2.7-Code

Experiential

Standard list rate

Input
$0.67
Output
$3.40
Cached input
$0.18
USD / 1M tokens

Catalog list rate. Plan allowances and temporary discounts are separate.

262.1K context235.9K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDkimi-k2.7-code

Inceptron

via OpenRouter

inceptron/int4 · quantization=int4

Input
$0.6712
Output
$3.35
Cached input
$0.18
USD / 1M tokens
262.1K context235.9K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/kimi-k2.7-code::inceptron/int4

CoreWeave

via OpenRouter

coreweave/int4 · quantization=int4

Input
$0.71
Output
$3.50
Cached input
$0.15
USD / 1M tokens
262.1K context235.9K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/kimi-k2.7-code::coreweave/int4

StreamLake

via OpenRouter

streamlake

Input
$0.7125
Output
$3.00
Cached input
$0.1425
USD / 1M tokens

Source discount 25%; rates as published

256K context32K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/kimi-k2.7-code::streamlake

Venice

via OpenRouter

venice/int4 · quantization=int4

Input
$0.75
Output
$3.50
Cached input
$0.16
USD / 1M tokens
256K context65.5K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/kimi-k2.7-code::venice/int4

SiliconFlow

via OpenRouter

siliconflow/fp8 · quantization=fp8

Input
$0.8592
Output
$3.80
Cached input
$0.1799
USD / 1M tokens
262.1K context235.9K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/kimi-k2.7-code::siliconflow/fp8

Novita

via OpenRouter

novita/int4 · quantization=int4

Input
$0.912
Output
$3.84
Cached input
$0.1824
USD / 1M tokens

Source discount 4%; rates as published

262.1K context235.9K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/kimi-k2.7-code::novita/int4

Phala

via OpenRouter

phala

Input
$0.95
Output
$4.00
Cached input
$0.19
USD / 1M tokens
262.1K context235.9K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/kimi-k2.7-code::phala

Nebius

via OpenRouter

nebius/fp4 · quantization=fp4

Input
$0.95
Output
$4.00
USD / 1M tokens
262.1K context235.9K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/kimi-k2.7-code::nebius/fp4

GMICloud

via OpenRouter

gmicloud/fp8 · quantization=fp8

Input
$0.95
Output
$4.00
Cached input
$0.19
USD / 1M tokens
262.1K context235.9K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/kimi-k2.7-code::gmicloud/fp8

Alibaba

via OpenRouter

alibaba/fp8 · quantization=fp8

Input
$0.95
Output
$4.00
Cached input
$0.19
USD / 1M tokens

Max prompt 229376 tokens

262.1K context16.4K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/kimi-k2.7-code::alibaba/fp8

Cloudflare

via OpenRouter

cloudflare

Input
$0.95
Output
$4.00
Cached input
$0.19
USD / 1M tokens
262.1K context235.9K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/kimi-k2.7-code::cloudflare

Moonshot AI

via OpenRouter

moonshotai/int4 · quantization=int4

Input
$0.95
Output
$4.00
Cached input
$0.19
USD / 1M tokens
262.1K context235.9K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/kimi-k2.7-code::moonshotai/int4

Moonshot AI

via OpenRouter

moonshotai/highspeed · tier=priority · quantization=int4

Input
$1.90
Output
$8.00
Cached input
$0.38
USD / 1M tokens
262.1K context235.9K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/kimi-k2.7-code::moonshotai/highspeed

Model specifications

Developer
moonshotai
Modality
Language
Context
262,144 tokens
Maximum output
235,929 tokens
Weights
Open weights
Provider listed
Jun 11, 2026
First discovered
Oct 16, 2026

Exact identities

  • openroutermoonshotai/kimi-k2.7-code
  • huggingfacemoonshotai/Kimi-K2.7-Code
  • experientialkimi-k2.7-code

Sources

Updated Oct 17, 2026

More from moonshotai

View all ↗
moonshotaiListed Jul 16

MoonshotAI: Kimi K3 (batch)

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

1M contextImage inputVideo inputNo reported score
No reported score
$2.28in$11.40out/ 1M tokens · USDDeepInfra · via OpenRouter · 2 endpointsdeepinfra/bf16 · quantization=bf16
moonshotaiListed Apr 14

MoonshotAI: Kimi K2.6

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks…

262.1K contextImage inputTool callingNo reported score
No reported score
$0.4323in$1.82out/ 1M tokens · USDBaidu · via OpenRouter · 23 endpointsbaidu/fp4 · quantization=fp4