NConnect
DocsDeepSeek V4 Flash + Prime Agent

TUTORIAL

How to run DeepSeek V4 Flash with Prime Agent

Run 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.

DeepSeek V4 FlashPrime Agent 5 minUpdated

Prime Agent is PrimeIntellect's RLM-style coding agent. It already speaks the OpenAI-compatible format Nebius serves, so NConnect points it straight at Token Factory with no proxy. DeepSeek V4 Flash is the fast, cost-effective member of the DeepSeek V4 family, with a 1M-token context window.

Prerequisites

Steps

  1. Install NConnect

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

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

  2. Add your Nebius API key

    nconnect configure

  3. Install Prime Agent

    Skip this if prime-agent is already on your PATH. In an interactive terminal, NConnect also offers to run this for you the first time you launch Prime Agent.

    curl -fsSL https://app.primeintellect.ai/prime-agent/install.sh | sh

  4. Launch Prime Agent on DeepSeek V4 Flash

    nconnect --model deepseek-ai/DeepSeek-V4-Flash prime
    You should see
    NConnect ▸ Launching Prime Agent with Nebius Token Factory (DeepSeek V4 Flash).

What NConnect does on launch

  • Declares Nebius as a custom provider in a config directory NConnect owns, ~/.nconnect/prime-agent. Your own ~/.prime/agent is never touched.
  • Keeps that directory between launches, because Prime Agent bootstraps its runtime there. The first launch takes longer; later ones start straight away.
  • Lists every Nebius model, so you can switch inside Prime Agent.

Track cost and add fallback

Prime Agent is a spawned harness, so by default it calls Nebius directly and NConnect reports $0.00. Route it through the daemon to meter every turn and get automatic fallback if DeepSeek V4 Flash is busy:

NCONNECT_METER=1 nconnect --model deepseek-ai/DeepSeek-V4-Flash prime

Then check spend with nconnect usage --last 7d. See Cost metering.

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