Moonshot AI
Hosted API for Kimi language and multimodal models
Moonshot AI develops the Kimi model family and provides a hosted API. Kimi K3 supports text, images, and video with a 1M-token context for coding, knowledge work, and reasoning.
Moonshot AI prices by model
Per 1M tokens, read off Moonshot AI's own pricing page on the date shown.
| Model | Input / 1M | Cached / 1M | Output / 1M | Checked | Notes |
|---|---|---|---|---|---|
| Kimi K3 | $3.00 | $0.30 | $15.00 | 2 Oct 2026 | Cache write $3.00 at 5-minute TTL, $6.00 at 1-hour TTL |
Moonshot AI Alternatives
Explore 126 products in the Inference APIs category. View all Moonshot AI alternatives.
Heabsy
EU inference API on its own GPUs in the EEA, with zero data retention and OpenAI- and Anthropic-compatible endpoints.
DeepInfra
Run the top AI models using a simple API, pay per use. Low cost, scalable and production ready infrastructure.
System1 Models
Hosted open decision models behind a Jev-compatible API, with an EU-only tier and a lower-cost Peer-to-Peer tier
Meta Model API
Meta's OpenAI-compatible API for its Muse models: 1M-context Muse Spark, image, transcription and SAM
Work on Moonshot AI? Feature it at the top of Inference APIs.
Is your product missing?