AI TOOLS RADAR
Submit
All models / MOONSHOTAI
moonshotai logo
moonshotai

MoonshotAI: Kimi K3

Source description (English)

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...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
1,048,576 tokens
Maximum output
943,718 tokens
Architecture
text+image+video->text
Tokenizer
Other
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

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

Input
$3
per 1M tokens
Output
$15
per 1M tokens
Cache read
$0.3
per 1M tokens
API

Model configuration

Default parameters

top_p
0.95

Reasoning

Reasoning required
No
Default parameters
max
Capabilities
max, high, low
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-k3","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textimagevideo
Output
text
Reasoning

Yes · max · high · low

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

20 providers

Checked: September 22, 2026

Live providers on OpenRouter

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

OpenRouter

InferenceNet

fp4
Context
1.0M
Maximum output
944K
Input
$1.5
Output
$7.5
Cache read
$0.15
Cache write
Not provided

Morph

Not provided
Context
1.0M
Maximum output
944K
Input
$1.625
Output
$9.1
Cache read
$0.1885
Cache write
Not provided

Relace

fp4
Context
1.0M
Maximum output
944K
Input
$1.7
Output
$8.5
Cache read
$0.17
Cache write
Not provided

Phala

Not provided
Context
1.0M
Maximum output
944K
Input
$2.07
Output
$10.35
Cache read
$0.207
Cache write
Not provided

Wafer

Not provided
Context
1.0M
Maximum output
944K
Input
$2.1
Output
$10.95
Cache read
$0.21
Cache write
Not provided

Sail Research

fp4
Context
1.0M
Maximum output
944K
Input
$2.144
Output
$10.758
Cache read
$0.244
Cache write
Not provided

Makora

Not provided
Context
1.0M
Maximum output
944K
Input
$2.55
Output
$12.75
Cache read
$0.256
Cache write
Not provided

DigitalOcean

Not provided
Context
1.0M
Maximum output
944K
Input
$2.55
Output
$12.95
Cache read
$0.255
Cache write
Not provided

DeepInfra

bf16
Context
1.0M
Maximum output
16K
Input
$2.85
Output
$14.25
Cache read
$0.285
Cache write
Not provided

Chutes

mxfp4
Context
1.0M
Maximum output
66K
Input
$3
Output
$15
Cache read
$0.3
Cache write
Not provided

Parasail

fp4
Context
1.0M
Maximum output
944K
Input
$3
Output
$15
Cache read
$0.3
Cache write
Not provided

Modal

mxfp4
Context
1.0M
Maximum output
944K
Input
$3
Output
$15
Cache read
$0.3
Cache write
Not provided

Together

Not provided
Context
1.0M
Maximum output
944K
Input
$3
Output
$15
Cache read
$0.3
Cache write
Not provided

Fireworks

Not provided
Context
1.0M
Maximum output
944K
Input
$3
Output
$15
Cache read
$0.3
Cache write
Not provided

BaseTen

fp8
Context
1.0M
Maximum output
262K
Input
$3
Output
$15
Cache read
$0.3
Cache write
Not provided

Moonshot AI

mxfp4
Context
1.0M
Maximum output
944K
Input
$3
Output
$15
Cache read
$0.3
Cache write
Not provided

Fireworks

Not provided
Context
1.0M
Maximum output
944K
Input
$3.3
Output
$16.5
Cache read
$0.33
Cache write
Not provided

Alibaba

Not provided
Context
1.0M
Maximum output
944K
Input
$3.45
Output
$17.25
Cache read
$0.345
Cache write
Not provided

Fireworks

Not provided
Context
1.0M
Maximum output
944K
Input
$4.5
Output
$22.5
Cache read
$0.45
Cache write
Not provided

Morph

Not provided
Context
1.0M
Maximum output
944K
Input
$6
Output
$22.5
Cache read
$0.6
Cache write
Not provided
moonshotai

4 models

All models
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: $0.7062Output: $3.3per 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: $0.95Output: $4per 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: $0.45Output: $2.25per 1M tokens
View model details →