Kimi K2.6 by Moonshot: open-weight agentic model with long-horizon coding, 300-agent swarms, video understanding, and 256K context.
Available on
Privacy
- Zero data retention
- Always-on
- Training
- No
- Region
- EU + US
OmniRoute is an open-source gateway you run yourself: one endpoint in front of 350 providers, with quota-aware fallback, token compression, and MCP support, built for Claude Code, Codex, Cursor, OpenCode, Cline and Copilot. Opper is listed in its provider catalogue, so you paste your Opper key once under Providers and every agent you point at OmniRoute can pick from Opper's 700+ models, EU-hosted routes included, alongside whatever else you have configured.
In OmniRoute (v3.8.51 or later), open Providers → API key providers, pick Opper and paste your key; on older builds add a custom OpenAI-compatible provider with base URL https://api.opper.ai/v3/compat. Then pick Kimi K2.6.
Kimi K2.6 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 | $0.87 | $4.08 |
| evroc | EU | Zero data retention | No | $1.57 | $6.29 |
| Inceptron | EU | Zero data retention | No | $0.60 | $3.41 |
| Nebius | EU | Enterprise | No | $0.95 | $4.00 |
| TensorX | EU | Zero data retention | No | $1.00 | $4.00 |
| DeepInfra | US | Zero data retention | No | $0.75 | $3.50 |
| Geodd | US | Zero data retention | No | $0.60 | $3.20 |
| Novita | US | Zero data retention | No | $0.80 | $3.40 |
| Azure | Multi | Enterprise | No | $0.95 | $4.00 |
| Fireworks | Multi | Zero data retention | No | $0.95 | $4.00 |
Kimi K2.6 by Moonshot: open-weight agentic model with long-horizon coding, 300-agent swarms, video understanding, and 256K context.
Anthropic's terminal coding agent. Run it on any model on Opper, not just Claude.
opper launch claudeOpenAI's open-source coding CLI. Run it on any model on Opper.
opper launch codexDeepSeek's open-source coding agent. Add Opper as a custom provider to run it on any model, not just DeepSeek's.
OpenAI-compatible