NConnect
DocsQwen 3.5 + OpenCode

TUTORIAL

How to run Qwen 3.5 with OpenCode

Run the OpenCode terminal agent on Alibaba's Qwen 3.5 397B, served by Nebius Token Factory through NConnect, without editing your OpenCode config.

Qwen 3.5 397BOpenCode 5 minUpdated

OpenCode already speaks the OpenAI-compatible format Nebius serves, so NConnect needs no proxy here: it launches OpenCode with Nebius configured as a provider for that one run. Qwen 3.5 397B is Alibaba's mixture-of-experts flagship for general and coding work, with a 262K-token context window.

Prerequisites

Steps

  1. Install NConnect

    This installs the CLI and the nopencode alias, plus Bun if needed.

    curl -fsSL https://nconnect.sh/install.sh | bash

  2. Add your Nebius API key

    nconnect configure

  3. Install OpenCode

    Skip this if opencode is already on your PATH. In an interactive terminal, NConnect also offers to run this for you the first time you launch OpenCode.

    npm install -g opencode-ai@latest

  4. Launch OpenCode on Qwen 3.5

    nconnect --model Qwen/Qwen3.5-397B-A17B opencode

    Arguments after opencode go to OpenCode, so run works for one-off tasks:

    nconnect --model Qwen/Qwen3.5-397B-A17B opencode run "summarize the open TODOs"

What NConnect does on launch

  • Passes a generated config with a nebius provider through the environment, and selects nebius/Qwen/Qwen3.5-397B-A17B on the command line so it wins over the default model in your own ~/.config/opencode.
  • Limits /models to the NConnect catalog, with real context limits and per-token prices, instead of hundreds of unrelated models.
  • Replaces the build agent's "You are OpenCode" framing with a neutral prompt, so the model doesn't misreport what it is.
  • Registers a @vision subagent pinned to a vision-capable model.

Switch models in the session

Use /models inside OpenCode to move between Nebius models without restarting. Pick a vision model such as Kimi K2.6 before pasting images.

More tutorials

Kimi K3Claude CodeHow to run Kimi K3 with Claude CodeUse Claude Code with Moonshot AI's Kimi K3 and its full 1M-token context, served by Nebius Token Factory through NConnect. No Anthropic account needed. Video included. 5 minRead tutorial GLM 5.3Codex CLIHow to run GLM 5.3 with Codex CLIRun OpenAI's Codex CLI on Z.ai's GLM 5.3, a 1M-context model for coding and tool use, served by Nebius Token Factory through NConnect. No OpenAI account needed. 5 minRead tutorial MiniMax M3Pi CodeHow to run MiniMax M3 with Pi CodeRun the Pi coding agent on MiniMax M3, a fast and low-cost reasoning model, served by Nebius Token Factory through NConnect with a temporary provider config. 5 minRead tutorial DeepSeek V4 FlashPrime AgentHow to run DeepSeek V4 Flash with Prime AgentRun PrimeIntellect's Prime Agent on DeepSeek V4 Flash, a fast 1M-context model for coding and agentic work, served by Nebius Token Factory through NConnect. 5 minRead tutorial