Back to Model Catalog
Large Language Modelkimi-k3

Kimi K3

2M Context

Moonshot AI flagship with ultra-long 2M lossless context, multi-document cross-referencing, and deep research synthesis.

AvailableDense TransformerProprietary

Params

2M Context

Context

2M

Max Output

64K

API Surface/v1/chat/completions

Capabilities & Performance

  • 2,000,000 token seamless retrieval without needle-in-haystack loss
  • Wholesale tier down to $1.429/M input

Transparent Pricing

LanePublic RateCached
Realtime API$1.86 / $9.29$0.371
Batch QueueBatch rates available on rollout$0.371

Prices per 1M tokens. Cached prompt rate applies on prefix hits.

100% OpenAI-Compatible Code

Drop-in API Examples

Get API Key
Python (OpenAI SDK)
from openai import OpenAI

client = OpenAI(
    base_url="https://api.batchin.tech/v1",
    api_key="BATCHIN_API_KEY"
)

resp = client.chat.completions.create(
    model="kimi-k3",
    messages=[{"role": "user", "content": "Benchmark system architecture performance and cost profile."}]
)

print(resp.choices[0].message.content)
JavaScript / Node.js
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.batchin.tech/v1",
  apiKey: process.env.BATCHIN_API_KEY,
});

const resp = await client.chat.completions.create({
  model: "kimi-k3",
  messages: [{ role: "user", content: "Benchmark system architecture performance and cost profile." }],
});

console.log(resp.choices[0]?.message?.content);
cURL / Shell
curl https://api.batchin.tech/v1/chat/completions \
  -H "Authorization: Bearer $BATCHIN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k3",
    "messages": [{"role":"user","content":"Benchmark system architecture performance and cost profile."}]
  }'

Related Next-Gen Models

View all models →
kimi-k2.7-codeMoonshot AI

Kimi K2.7 Code

Specialized coding intelligence model from Moonshot AI with deep understanding of complex frameworks and full-stack tasks.

View model →
qwen3.7-maxQwen

Qwen 3.7 Max

Alibaba flagship reasoning model with native 1M context window and state-of-the-art benchmark capabilities.

View model →
deepseek-v4-proDeepSeek

DeepSeek V4 Pro

DeepSeek next-gen MoE reasoning flagship for complex architectural design, autonomous coding loops, and math proofs.

View model →
Kimi K3 | BatchIn