Kimi K3 by Moonshot: open-weight 2.8 trillion parameter MoE with 104 billion active, native vision, and a 1M token context for long-horizon coding and agentic work.
Available on
Privacy
- Zero data retention
- Always-on
- Training
- No
- Region
- EU + US
Zed is a high-performance, open-source code editor from Zed Industries, the team that created Atom, written from scratch in Rust with AI and collaboration built in. Its agent panel works with any OpenAI-compatible provider you add, and API keys stay in your system keychain. Add qynio as a provider and Zed's agent runs on any of 700+ models, with a choice of EU or US hosting on one key.
Paste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with qynio for you.
Kimi K3 runs on the routes below. Route only to EU providers when your data has to stay in Europe.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| Berget | EU | Zero data retention | No | $3.49 | $17.43 |
| Nebius | EU | Not by default | No | $3.00 | $15.00 |
| Nextbit | EU | Not by default | No | $3.75 | $18.75 |
| Sference | EU | Zero data retention | No | $2.25 | $11.25 |
| TensorX | EU | Zero data retention | No | $3.00 | $15.00 |
| DigitalOcean | US | Not by default | No | $2.85 | $14.25 |
| Morph | US | Not by default | No | $2.60 | $14.00 |
| Morph | US | Not by default | No | $6.00 | $22.50 |
| Novita | US | Zero data retention | No | $3.00 | $15.00 |
| Wafer | US | Zero data retention | No | $3.00 | $12.75 |
| Fireworks | Multi | Zero data retention | No | $3.00 | $15.00 |
| Moonshot AI | Multi | Not by default | Yes | $3.00 | $15.00 |
Kimi K3 by Moonshot: open-weight 2.8 trillion parameter MoE with 104 billion active, native vision, and a 1M token context for long-horizon coding and agentic work.
Point Cursor's OpenAI base URL at qynio to run it on any of 700+ models.
OpenAI-compatibleCline's OpenAI-Compatible provider points straight at qynio's gateway.
OpenAI-compatibleAdd qynio as an OpenAI provider in config.yaml and Continue's chat, edit and autocomplete run on any model.
OpenAI-compatible