MA
chatMoonshot AI
Kimi K2.6
Moonshot's large mixture-of-experts model with strong reasoning, agentic tool-use and long-context performance. Fast and reliable for production chat.
moonshotai/kimi-k2.6Test it live
Live playgroundMAKimi K2.6in-browser demo
Test Kimi K2.6 live
Send a message and watch the model respond. Multi-turn — it remembers the conversation.
More chat models
Llama 3.3 70B Instruct
Meta
Meta's flagship 70B instruct model — 405B-class quality at a fraction of the cost. Great default for production chat.
meta/llama-3.3-70b-instructInput / 1M
$0.20
Output / 1M
$0.20
Llama 4 Maverick
Meta
Meta's latest flagship mixture-of-experts model. Frontier quality for demanding reasoning and generation.
meta/llama-4-maverick-17b-128e-instructInput / 1M
$0.60
Output / 1M
$0.60
Llama 3.1 8B Instruct
Meta
Fast, cheap and capable. Ideal for high-volume classification, routing and lightweight chat.
meta/llama-3.1-8b-instructInput / 1M
$0.05
Output / 1M
$0.05