Moonshot (Kimi) / kimi-k2.6
Kimi K2.6 stands out for Kimi model for long-horizon coding and tool use and 262K context with reliable agent workflows. It is best suited to large codebase work and multi-step tool workflows.
Context
262K
token
Input
$0.855
/ 1M tokens
Output
$3.60
/ 1M tokens
Quality
#69
Elo 1120
Overview
Kimi K2.6 stands out for Kimi model for long-horizon coding and tool use and 262K context with reliable agent workflows. It is best suited to large codebase work and multi-step tool workflows.
Tool calling
Can call tools or functions, so product flows can connect model output to backend actions.
Streaming
Supports streamed responses for chat, assistants, and interfaces that need visible incremental output.
Model maker
Moonshot (Kimi)
Called through SeaLink's unified account, balance, and OpenAI-compatible API.
Protocol
OpenAI-compatible Chat Completions
Base URL: https://api.sealink.io/v1
Pricing
The final charge follows generated usage and the applicable selector, such as resolution, duration, input type, or provider unit.
API
model
kimi-k2.6base_url
https://api.sealink.io/v1Auth
Bearer $SEALINK_API_KEYcurl https://api.sealink.io/v1/chat/completions \-H "Authorization: Bearer $SEALINK_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "kimi-k2.6","messages": [{"role": "user", "content": "Hello."}]}'
from openai import OpenAIclient = OpenAI(base_url="https://api.sealink.io/v1", api_key="<your-sealink-key>")resp = client.chat.completions.create(model="kimi-k2.6",messages=[{"role": "user", "content": "Hello."}],)print(resp.choices[0].message.content)
import OpenAI from "openai";const client = new OpenAI({baseURL: "https://api.sealink.io/v1",apiKey: process.env.SEALINK_API_KEY,});const resp = await client.chat.completions.create({model: "kimi-k2.6",messages: [{ role: "user", content: "Hello." }],});console.log(resp.choices[0].message.content);