AI TOOLS RADAR
Explore
All models / MOONSHOTAI
moonshotai logo
moonshotai

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. $0.66 per million input tokens, $3.40 per million output tokens. 262,144 token context window, maximum output of 262,144 tokens. Higher uptime with 15 providers. Includes independent benchmarks from Artificial Analysis.

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
262,144 tokens
Maximum output
235,929 tokens
Architecture
text+image->text
Tokenizer
Other
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.66
/M tokens
Output
$3.4
/M tokens
Cache read
$0.18
/M tokens
API

Model configuration

Reasoning

Moderated
Yes
Default parameters
Yes
API

Quick start

Call this exact model ID through OpenRouter’s OpenAI-compatible API.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"moonshotai/kimi-k2.7-code","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textimage
Output
text
Reasoning

Yes

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

16 providers

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Inceptron

int4
Context
262K
Maximum output
236K
Input
$0.660
Output
$3.40
Cache read
$0.180
Cache write
Not provided

DeepInfra

fp4
Context
262K
Maximum output
16K
Input
$0.680
Output
$3.40
Cache read
$0.136
Cache write
Not provided

Ambient

unknown
Context
262K
Maximum output
236K
Input
$0.690
Output
$3.49
Cache read
$0.140
Cache write
Not provided

CoreWeave

int4
Context
262K
Maximum output
236K
Input
$0.710
Output
$3.50
Cache read
$0.150
Cache write
Not provided

Venice

int4
Context
256K
Maximum output
66K
Input
$0.750
Output
$3.50
Cache read
$0.160
Cache write
Not provided

Parasail

int4
Context
262K
Maximum output
236K
Input
$0.760
Output
$3.50
Cache read
$0.160
Cache write
Not provided

ModelRun

fp4
Context
262K
Maximum output
236K
Input
$0.850
Output
$3.75
Cache read
$0.160
Cache write
Not provided

SiliconFlow

fp8
Context
262K
Maximum output
236K
Input
$0.859
Output
$3.80
Cache read
$0.180
Cache write
Not provided

Novita

int4
Context
262K
Maximum output
236K
Input
$0.912
Output
$3.84
Cache read
$0.182
Cache write
Not provided

Nebius

fp4
Context
262K
Maximum output
236K
Input
$0.950
Output
$4.00
Cache read
Not provided
Cache write
Not provided

GMICloud

fp8
Context
262K
Maximum output
236K
Input
$0.950
Output
$4.00
Cache read
$0.190
Cache write
Not provided

Cloudflare

unknown
Context
262K
Maximum output
236K
Input
$0.950
Output
$4.00
Cache read
$0.190
Cache write
Not provided

Moonshot AI

int4
Context
262K
Maximum output
236K
Input
$0.950
Output
$4.00
Cache read
$0.190
Cache write
Not provided

Together

unknown
Context
262K
Maximum output
236K
Input
$0.950
Output
$4.00
Cache read
$0.190
Cache write
Not provided

Alibaba

fp8
Context
262K
Maximum output
16K
Input
$0.950
Output
$4.00
Cache read
$0.190
Cache write
Not provided

Moonshot AI

int4
Context
262K
Maximum output
236K
Input
$1.90
Output
$8.00
Cache read
$0.380
Cache write
Not provided
moonshotai

models

All models
moonshotai logomoonshotai

MoonshotAI: Kimi K3

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...

Context
1.0M
Input
text · image · video
Output
text
Input: $3.00Output: $15.00per 1M tokens
View model details →
moonshotai logomoonshotai

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...

Context
1.0M
Input
text · image · video
Output
text
Input: $3.00Output: $15.00per 1M tokens
View model details →
moonshotai logomoonshotai

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 across Python, Rust, and Go, and...

Context
262K
Input
text · image
Output
text
Input: $0.950Output: $4.00per 1M tokens
View model details →
moonshotai logomoonshotai

MoonshotAI: Kimi K2.5

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

Context
262K
Input
text · image
Output
text
Input: $0.450Output: $2.25per 1M tokens
View model details →