LLM Reference
Together AI

Using Kimi K2.6 on Together AI

Implementation guide · Kimi K2 · Moonshot AI

ServerlessOpen Source

Quick Start

  1. 1
    Create an account at Together AI and generate an API key.
  2. 2
    Use the Together AI SDK or REST API to call moonshotai/Kimi-K2.6 — see the documentation for request format.
  3. 3
    You'll be billed $1.20/1M input, $4.50/1M output tokens. See full pricing.

Code Examples

Install
pip install together
API key
TOGETHER_API_KEY
Model ID
moonshotai/Kimi-K2.6

Together uses "organization/model-name" format, e.g. "meta-llama/Llama-4-Scout-17B-16E-Instruct" or "Qwen/QwQ-32B". See the Together model catalog for the exact ID.

from together import Together

client = Together()  # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
    model="moonshotai/Kimi-K2.6",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

About Together AI

Platform for running open-source and proprietary LLMs

Together AI is a platform for running open-source and proprietary LLMs with fast serverless and dedicated endpoints at competitive inference pricing.

Pricing on Together AI

TypePrice (per 1M)
Input tokens$1.20
Output tokens$4.50

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsPrompt Caching

About Kimi K2.6

Kimi K2.6 is Moonshot AI's multimodal agentic coding model, released April 20 2026 under a Modified MIT license. Built on a 1-trillion-parameter MoE architecture (32B active, 384 experts with 8 selected per token plus 1 shared expert, 61 layers), it features a 262K context window and up to 65,536 output tokens. Supports native image and video inputs (screenshots, PDFs, spreadsheets). Designed for long-horizon coding with agent swarms of up to 300 sub-agents and 4,000 coordinated steps; Moonshot AI cites 200–300 sequential tool calls without task drift. Key benchmarks: SWE-bench Verified 80.2%, SWE-bench Pro 58.6%, LiveCodeBench v6 89.6%, GPQA Diamond 90.5%, Terminal-Bench 2.0 66.7%. Chatbot Arena Elo 1454 (2026-04-28 snapshot).

Model Specs

Released2026-04-20
Parameters1T
Context262k
ArchitectureMixture of Experts
Knowledge cutoff2025-04

Provider

Together AI
Together AI

San Francisco, California, United States