LLM Reference
Together AI

Kimi K2.6 on Together AI

Kimi K2 · Moonshot AI

ServerlessOpen Source

Last refreshed 2026-06-30. Next refresh: weekly.

Why use Kimi K2.6 on Together AI?

Together AI offers Kimi K2.6 with pay-as-you-go pricing at $1.20/1M input tokens. Together AI is a platform for running open-source and proprietary LLMs with fast serverless and dedicated endpoints at competitive inference pricing.

Compare Kimi K2.6 across 9 providers to find the best fit for your use case
Input / 1M
$1.20
Output / 1M
$4.50
Cache
read $0.20
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install together
Auth
export TOGETHER_API_KEY=...
Call
from together import Together
client = Together()  # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
    model="moonshotai/Kimi-K2.6",
Model ID
moonshotai/Kimi-K2.6

Request example

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)

Gotchas

  • Use provider model ID "moonshotai/Kimi-K2.6", not the LLMReference slug "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.
  • The examples expect TOGETHER_API_KEY; rename it only if your application config maps the new variable.

Compare Kimi K2.6 Across Providers

ProviderInput (per 1M)Output (per 1M)
Cloudflare Workers AI$0.95$4.00
NVIDIA NIM
Moonshot AI Kimi$0.95$4.00
Fireworks AI$0.95$4.00
OpenRouter$0.73$3.49
View all 9 providers →

Pricing

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

Capabilities

VisionMultimodalReasoningJSON / Tool 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.

Get Started