AI TOOLS RADAR
All models / MOONSHOTAI
moonshotai logo
moonshotai

MoonshotAI: Kimi K2.6

Source description (English)

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...

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
$0.65
per 1M tokens
Output
$3.41
per 1M tokens
Cache read
$0.15
per 1M tokens
API

Model configuration

Reasoning

Reasoning required
No
Default parameters
Yes
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"moonshotai/kimi-k2.6","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

17 providers

Checked: October 11, 2026

Live providers on OpenRouter

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

OpenRouter

Baidu

fp4
Context
262K
Maximum output
236K
Input
$0.4341
Output
$1.828
Cache read
$0.0731
Cache write
Not provided

Inceptron

int4
Context
262K
Maximum output
236K
Input
$0.4344
Output
$2.45
Cache read
$0.1077
Cache write
Not provided

Chutes

int4
Context
262K
Maximum output
66K
Input
$0.5
Output
$2.85
Cache read
$0.05
Cache write
Not provided

DigitalOcean

Not provided
Context
262K
Maximum output
236K
Input
$0.57
Output
$2.4
Cache read
$0.114
Cache write
Not provided

StreamLake

fp8
Context
256K
Maximum output
230K
Input
$0.5985
Output
$2.52
Cache read
$0.1008
Cache write
Not provided

CoreWeave

fp4
Context
262K
Maximum output
236K
Input
$0.65
Output
$3.41
Cache read
$0.15
Cache write
Not provided

Crusoe

bf16
Context
262K
Maximum output
236K
Input
$0.7
Output
$3.5
Cache read
$0.35
Cache write
Not provided

DeepInfra

fp4
Context
262K
Maximum output
16K
Input
$0.75
Output
$3.5
Cache read
$0.15
Cache write
Not provided

Venice

int4
Context
256K
Maximum output
66K
Input
$0.75
Output
$3.5
Cache read
$0.16
Cache write
Not provided

Parasail

int4
Context
262K
Maximum output
236K
Input
$0.75
Output
$3.5
Cache read
$0.16
Cache write
Not provided

SiliconFlow

fp8
Context
262K
Maximum output
236K
Input
$0.77
Output
$3.4
Cache read
$0.14
Cache write
Not provided

Novita

Not provided
Context
262K
Maximum output
236K
Input
$0.8
Output
$3.4
Cache read
$0.16
Cache write
Not provided

GMICloud

fp8
Context
262K
Maximum output
236K
Input
$0.855
Output
$3.6
Cache read
$0.144
Cache write
Not provided

AtlasCloud

int4
Context
262K
Maximum output
236K
Input
$0.95
Output
$4
Cache read
$0.16
Cache write
Not provided

Cloudflare

Not provided
Context
262K
Maximum output
236K
Input
$0.95
Output
$4
Cache read
$0.16
Cache write
Not provided

Moonshot AI

int4
Context
262K
Maximum output
236K
Input
$0.95
Output
$4
Cache read
$0.16
Cache write
Not provided

Phala

Not provided
Context
262K
Maximum output
236K
Input
$1.09
Output
$4.6
Cache read
$0.37
Cache write
Not provided
moonshotai

4 models

All models
moonshotai logomoonshotai

MoonshotAI: Kimi K3.1 Pro

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...

Context
1.0M
Input
text · image · video
Output
text
Input: $2Output: $10per 1M tokens
View model details →
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: $0.191Output: $20per 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: $2.28Output: $11.4per 1M tokens
View model details →
moonshotai logomoonshotai

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
262K
Input
text · image
Output
text
Input: $0.6712Output: $3.35per 1M tokens
View model details →