DeepSeek Harness logo

Run DeepSeek Harness on Qwen3.8 Flash-Next

by DeepSeekCoding agent

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.

RunDeepSeek Harness logoDeepSeek Harnessonin

Connect DeepSeek Harness to Qwen3.8 Flash-Next

Set up with agents

Paste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.

Get your API key

Where you can run it

Qwen3.8 Flash-Next runs on the routes below. Route only to EU providers when your data has to stay in Europe.

ProviderRegionZero data retentionTrainingInputOutput
SferenceEUZero data retentionNo$0.20$0.50
TensorXEUZero data retentionNo$0.20$0.50

The model

by Alibaba

Qwen3.8 Flash-Next is a natively multimodal MoE model from Alibaba with 125B total / 6B active parameters and a 256K context window. It targets frontier-grade coding and agentic work at very low active-parameter cost (Artificial Analysis intelligence index 55.8, coding index 73.1).

Available on

Pricing from$0.20/ 1M input$0.50/ 1M output262Kcontext

Privacy

Zero data retention
Always-on
Training
No
Region
EU

More apps on Opper

Run DeepSeek Harness on Qwen3.8 Flash-Next

One key, 700+ models, a choice of region, and zero data retention. Switch the model behind your app without changing your workflow.

Get startedView Documentation