Kimi K3 lands on RunPod: 2.8T params, 1M context, $3/$15 per 1M tokens
Kimi_Moonshot · x · 2026-09-10
RunPod announces Kimi K3 via its Moonshot AI partnership — since its July launch it has become one of the fastest-growing models on RunPod's public endpoints. Users can call the managed endpoint (OpenAI-compatible, model kimi-k3, streaming supported) or self-deploy on an 8xB300 pod.
Specs: 2.8T parameters (16 of 896 experts active), 1M token context, pricing of $3.00/1M input and $15.00/1M output tokens, under the Kimi-K3 model license — aimed at long-horizon coding and agentic knowledge work. Moonshot's official account reshared the announcement.
More from Infra
- Analyst: DeepSeek's latest change is a big win for token efficiency, moving toward OpenAI's regime — teortaxesTex · 2026-09-10
- Acellera tests 7 LLM+harness combos on drug discovery: one RTX 5090 holds up — gdefabritiis · 2026-09-10
- Engram embeddings load overlapped with GPU compute, so fetch time costs nothing — bookwormengr · 2026-09-10
- Mac mini tested: local 35B runtime hits Haiku-level scores but falls short for agents — PawelHuryn · 2026-09-10
- Miles ships Day-0 RL support for DeepSeek-V4.1-Flash with KL held at 0.0012–0.0017 — ying11231 · 2026-09-10
- The data center is a symbol: why debunked claims about AI infrastructure still spread — ShakeelHashim · 2026-09-10