DeepSeek Harness (dsh) is DeepSeek's open-source agent harness, released under MIT and built so that everything is a plugin, from the model adapter and the tool registry to the agent loop itself. Start it with npx @deepseek-ai/dsh web and it opens a local web UI where the agent reads and edits your workspace, runs commands, and keeps a plan, with a headless profile for one-shot jobs from the terminal. On Opper it runs on any of 700+ models rather than DeepSeek's own alone: add Opper as a custom provider and you get one key, automatic fallbacks, and a choice of region.
DeepSeek HarnessoninPaste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.
Nemotron Nano 12B v2 VL runs on the routes below. Route only to EU providers when your data has to stay in Europe. One route also sells flex and priority processing: the same model at another price, picked per request with service_tier. How service tiers work.
| Provider | Region | Zero data retention | Training | Input | Output | Cache read | ||
|---|---|---|---|---|---|---|---|---|
| US | No | $0.06 | $0.24 | Input price | ||||
| US | No | $0.20 | $0.60 | Input price | Not offered on this route | Not offered on this route |
NVIDIA Nemotron Nano 12B VL is a 12B multimodal vision-language model for document intelligence, visual question-answering, and video understanding.
Step-by-step setup for running DeepSeek Harness on each of these models through Opper.
Anthropic's terminal coding agent. Run it on any model on Opper, not just Claude.
opper launch claude
OpenAI's open-source coding CLI. Run it on any model on Opper.
opper launch codex
GitHub's terminal coding agent. Point its provider variables at Opper to run it on any model, no Copilot plan required.
OpenAI-compatible