Qwen3 14B, Alibaba's April 2025 dense model with switchable thinking and direct modes for reasoning and tool use at 40K context.
Available on
Pricing from$0.10/ 1M input$0.22/ 1M output41Kcontext
Privacy
- ZDR
- Training
- No
- Region
- EU + US
Run DeepSeek Harness on Qwen3 14B
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 Harnessonin
DeepSeek HarnessoninConnect DeepSeek Harness to Qwen3 14B
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.
Where you can run it
Qwen3 14B 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 | ||
|---|---|---|---|---|---|---|---|---|
| EU | No | — | — | Input price | Not offered on this route | Not offered on this route | ||
| EU | No | $0.10 | $0.22 | Input price | Not offered on this route | Not offered on this route | ||
| US | No | $0.12 | $0.24 | Input price |
The model
Run DeepSeek Harness on other models
Step-by-step setup for running DeepSeek Harness on each of these models through Opper.
GPT-6 SolGPT-6 LunaClaude Opus 5.5Grok 4.7MiMo V2.6 ProLing-3.0-flash-FinDeepSeek V4.1 FlashLing-3.0-flash-VLGPT-6 AstraQwen3.8-MaxGemini 3.8 FlashMuse Spark 1.3 ContributorClaude Fable 5.1GLM-5.3-FlashQwen3.8 Flash-NextGLM-5.3Qwen3.8 27BDeepSeek V4 ProGemini 3.7 FlashGrok 4.6Qwen3.8-2.4T-A95BInkling-SmallClaude Opus 5Gemini 3.6 FlashKimi K3GPT-5.6 SolGPT-5.6 TerraGPT-5.6 LunaGrok 4.5Claude Sonnet 5GLM-5.2Kimi K2.7 CodeClaude Fable 5MiniMax M3Claude Opus 4.8Qwen3.7-MaxKimi K2.6Claude Opus 4.7GLM 5.1Gemini 3.1 Pro PreviewClaude Sonnet 4.6GLM 4.7GPT-5Grok 4.20 ReasoningDeepSeek V4 Flash VisionHy4 PreviewQwen3.8 FlashMiniMax H3MiMo V2.6 FlashSCX-coderMAGPiEGreen LGreen RSee all 700+ models
More apps on Opper
Claude Code
Anthropic's terminal coding agent. Run it on any model on Opper, not just Claude.
Coding
opper launch claude
Codex
OpenAI's open-source coding CLI. Run it on any model on Opper.
Coding
opper launch codex
GitHub Copilot CLI
GitHub's terminal coding agent. Point its provider variables at Opper to run it on any model, no Copilot plan required.
Coding
OpenAI-compatible