Models / Kimi K3

Kimi K3

Open 3T-class model for long-horizon coding and knowledge work

  • Pay-as-you-go — no credit card to start

  • Drop-in OpenAI-compatible API

  • Match closed model quality at 80% lower cost

  • Drop-in OpenAI-compatible API

  • Match closed model quality at 80% lower cost

  • Served in the EU: your data stays in-region

Contact Sales
Get Started
  • cURL
  • Python
  • Typescript

Endpoint:

moonshotai/Kimi-K3

curl -X POST "https://api.together.xyz/v1/chat/completions" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/Kimi-K3",
    "messages": [
      {
        "role": "user",
        "content": "What are some fun things to do in New York?"
      }
    ]
}'

from together import Together

client = Together()

response = client.chat.completions.create(
  model="moonshotai/Kimi-K3",
  messages=[
    {
      "role": "user",
      "content": "What are some fun things to do in New York?"
    }
  ]
)
print(response.choices[0].message.content)

import Together from 'together-ai';
const together = new Together();

const completion = await together.chat.completions.create({
  model: 'moonshotai/Kimi-K3',
  messages: [
    {
      role: 'user',
      content: 'What are some fun things to do in New York?'
     }
  ],
});

console.log(completion.choices[0].message.content);
Trusted by

Why Kimi K3 on Together AI

We build for production workloads — not just demos

Leading price performance

Full-stack optimizations deliver higher throughput and lower latency than the leading open source implementations on identical hardware.

Run it your way

Serverless scales to your traffic with per token pricing. Dedicated gives you isolated GPUs tuned to your workload.

Backed by research
that ships

Inference performance is driven by continuous optimization across kernels, scheduling, and runtime systems.

Kimi K3

Endpoint:

moonshotai/Kimi-K3

About

Kimi K3 is Moonshot AI's most capable model and the first open model at the 3-trillion-parameter class, with 2.8T total parameters activating 16 of 896 experts per token. It is built on Kimi Delta Attention and Attention Residuals, two architectural changes to how information flows across sequence length and model depth, with native vision and a 1-million-token context window. The model is designed for long-horizon work: sustaining extended engineering sessions across large repositories, carrying multi-step research and document tasks end to end, and reading screenshots, charts, and documents inside the same model. It runs at maximum thinking effort at launch, and weights are released under an open license. Available on Together AI.

‍

Pricing

  • Input
    $3.00
    / 1M tokens
  • output
    $15.00
    / 1M tokens
  • cache
    $0.30
    / 1M cached

Performance benchmark

Kimi K3 vs competitor closed-source models
GPQA diamond rating
93.5%
Kimi K3
94.1%
GPT-5.6 Sol
93.2%
Claude Opus 5
93.1%
Grok 4.5
92.6%
Claude Fable 5
91.1%
GPT-5.6 Luna
Model specifications
  • Deployment
    Serverless
    Dedicated
    Provisioned Throughput
  • Features
    JSON Mode
    Function Calling
  • Parameters
    2.8T
  • Context length
    1.05M
  • Input modalities
    Text
    Image
  • Output modalities
    Text
View Docs
Deploy model

Deployment options

Run models using different deployment options depending on latency needs, traffic patterns, and infrastructure control.

  • Serverless Inference

  • Provisioned 
Throughput

  • Dedicated Model 
Inference

  • Dedicated Container 
Inference

Serverless Inference

A fully managed real-time or batch inference API with access to dozens of the most popular AI models.

2.75x faster

Best for

Variable or unpredictable traffic

Rapid prototyping and iteration

Cost-sensitive or early-stage production workloads

Get started
Explore Docs

Provisioned 
Throughput

Reserved token capacity with SLA guarantees. Priced in PTUs, a normalized throughput unit.

up to 90% lower cost

Best for

Production workloads

Reliability guarantees

Predictable pricing

Contact Sales
Explore Docs

Dedicated Model
Inference

An inference endpoint backed by reserved, isolated compute resources and Together AI inference research.

3.18x faster with ATLAS

Best for

Predictable or steady traffic

Latency-sensitive applications

High-throughput production workloads

Get started
Explore Docs

Dedicated Container
Inference

Run inference with your own engine and model on fully-managed, scalable infrastructure.

100B+ params · 2–3x savings

Best for

Generative media models

Non-standard runtimes

Custom inference pipelines

Contact sales
Explore Docs

Customers running inference in production

View All Stories
Young man with black hair wearing a dark jacket and sunglasses standing near a waterfall.

  • 6×

    cost reduction

  • <400ms

    p95 model latency

  • Weekly

    model deployments

"Low latency is especially important for voice because there’s a much higher UX bar. Together helped us push latency down by optimizing our models with techniques like speculative decoding, and they’ve been a reliable production partner — proactive about risks and fast when issues come up."

Max Lu

Head of Research, Decagon

Smiling young man with light brown hair wearing a blue patterned shirt in a softly blurred indoor setting.

  • ~30%

    Cost savings

"Together has helped us deploy VyUI, our state-of-the-art computer AI model. We had multiple in-depth meetings where we brainstormed how we could satisfy our model's custom technical requirements while still leveraging Together's infrastructure for efficient, load-balanced inference."

Luca Weihs

Co-founder, Vercept

Smiling man with short dark hair wearing a black shirt and dark gray blazer against a light background.

"Together AI offers optimized performance at scale, and at a lower cost than closed-source providers – all while maintaining strict privacy standards."

Vineet Khosla

CTO, The Washington Post

View all stories

Production-grade
security and data privacy

We take security and compliance seriously, with strict data privacy controls to keep your information protected. Your data and models remain fully under your ownership, safeguarded by robust security measures.

Learn More

We take security and compliance seriously, with strict data privacy controls to keep your information protected. Your data and models remain fully under your ownership, safeguarded by robust security measures.

  • NVIDIA logo with text Preferred Partner on a black background.
    preferred partner
  • SOC 2 Type II
  • ISO 27001:2022