Moonshot

MoonshotAI: Kimi K2.6

moonshotai/kimi-k2.6-20260420Hugging Face ↗

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

toolsstructuredreasoningimage in
Data source

MoonshotAI: Kimi K2.6 usage over time

OpenRouter share of tokens, by day.

View
Tidelines — LLM usage and market share

MoonshotAI: Kimi K2.6 holds 0.19% today, down from 0.77% at the start of the visible window.

Data: OpenRouter as of 2026-09-03 · Source: tidelines.ai/models/moonshotai-kimi-k2-6-20260420

Rank history

Tidelines — LLM usage and market share
Data: OpenRouter as of 2026-09-03 · Source: tidelines.ai/models/moonshotai-kimi-k2-6-20260420

Adoption curve vs the pantheon

MoonshotAI: Kimi K2.6's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?

Tidelines — LLM usage and market share
Data: OpenRouter as of 2026-09-03 · Source: tidelines.ai/models/moonshotai-kimi-k2-6-20260420

Citable stat

As of 2026-09-03, MoonshotAI: Kimi K2.6 holds 0.2% of OpenRouter token share, down 0.05pp over 30 days. Source: Tidelines (OpenRouter).

Cost per session

Median dollars spent on one MoonshotAI: Kimi K2.6 session, by coding agent and session length.

Tidelines — LLM usage and market share

Token rate sets the price; session length and reasoning set the bill.

Agent1 turn2–9 turns10–49 turns50+ turns
Hermes Agent$0.0075$0.030$0.238$1.49

Compare every model's session cost →

Data: OpenRouter session-cost dataset as of 2026-08-30 · Source: tidelines.ai/models/moonshotai-kimi-k2-6-20260420

Where to run it

MoonshotAI: Kimi K2.6 pricing by provider

Tidelines — LLM usage and market share

Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.

MoonshotAI: Kimi K2.6 is served by 20 tracked endpoints on OpenRouter. The cheapest output price is $2.45 per million tokens from Decart, and the most expensive is $4.60 from Phala. The largest context window offered is 262k tokens. Prices are list rates and refresh daily.

ProviderInput $/MOutput $/MContextUptime
Decart$0.52$2.45262k99.87%
Inceptron$0.51$2.50262k98.70%
StreamLake$0.60$2.52256k99.02%
Chutes$0.58$3.40262k99.43%
SiliconFlow$0.77$3.40262k99.85%
Novita$0.80$3.40262k99.76%
CoreWeave$0.65$3.41262k99.97%
Crusoe$0.70$3.50262k90.21%
DeepInfra$0.75$3.50262k
Venice$0.75$3.50256k5.94%
Parasail$0.75$3.50262k99.84%
GMICloud$0.85$3.60262k97.70%
DigitalOcean$0.95$4.00262k99.21%
Baidu$0.95$4.00262k100.00%
AtlasCloud$0.95$4.00262k98.85%
Cloudflare$0.95$4.00262k100.00%
Moonshot AI$0.95$4.00262k100.00%
BaseTen$0.95$4.00262k
Fireworks$0.95$4.00262k
Phala$1.09$4.60262k99.17%