This column explains what DeepSeek TUI is, how to install and configure it, how the Pro-orchestrates-Flash-executes architecture keeps costs low, and where it fits relative to Claude Code.
Developer website
We place the developer website in the sources and setup section, not in pricing, because DeepSeek TUI is an independent developer tool rather than a stocked Coding Plan. Use the site for product orientation, then confirm releases and technical details from GitHub before installing.
DeepSeek TUI reads your project files, edits code, runs shell commands, manages git, and searches the web — all inside your terminal. It is a development tool, not a conversational interface like the DeepSeek web chat.
The RLM (rlm_query) feature lets deepseek-v4-pro coordinate up to 16 deepseek-v4-flash workers that analyze sub-tasks in parallel. Pro handles the high-level strategy; Flash workers do the cheaper, parallel grunt work.
DeepSeek TUI is built for DeepSeek V4's 1M-token context window. With intelligent compaction and prefix-cache optimization, it can work across an entire codebase without losing track of earlier turns.
Complete guide to DeepSeek TUI, the Rust-powered terminal coding agent built for DeepSeek V4. Covers npm/Cargo install, API key setup, Plan/Agent/YOLO modes, RLM parallel reasoning, keyboard shortcuts, skills system, cost tracking, and how it compares to Claude Code.
DeepSeek TUI is a terminal-native coding agent — a single compiled Rust binary that talks to the DeepSeek API. You type prompts into a terminal interface, and the agent can read and edit files, execute shell commands, manage git branches, search the web, and call out to MCP servers for extra capabilities. It is not a terminal emulator (that's Warp) and not a chat bot (that's the DeepSeek web app). It's a tool-using agent that lives in your terminal.
If you are looking for the DeepSeek TUI developer website, use https://deepseek-tui.com. It belongs in the developer-resource section of this guide because it helps users orient around the tool before reading release notes, architecture docs, and configuration details.
The canonical install surface has now moved to CodeWhale. The current stable baseline is v0.8.50, the README leads with `codewhale`, and npm/Cargo/manual-download examples all use `codewhale` plus `codewhale-tui`. If you do not want Node.js in the install chain, the official docs still list Homebrew, Cargo, Docker, Scoop, or verified release binaries from GitHub.
On first launch you will be prompted for a DeepSeek API key. You can also set it explicitly. The current README says user config lives at ~/.codewhale/config.toml, with ~/.deepseek/config.toml kept only as a legacy fallback. Project-specific overrides now live in <workspace>/.codewhale/config.toml, while <workspace>/.deepseek/config.toml remains compatibility-only (api_key and base_url are still denied at the project level for security).
DeepSeek TUI gives you three escalating levels of autonomy. You cycle between them with Tab in the TUI, or pass them as flags on the command line.
One of the most interesting features is RLM (rlm_query), which farms out 1–16 cheap deepseek-v4-flash child agents to analyze a problem in parallel. The Pro model orchestrates the overall strategy; Flash workers handle the parallel grunt work. This is the "Pro does the big job, Flash does the small jobs" architecture the tool was designed around.
Verified Summary
This section compresses the most common questions about DeepSeek TUI into a source-backed table, useful for both readers and search crawlers.
| Search intent | Verified answer | Why it matters |
|---|---|---|
| What changed in the latest stable install docs? | As of June 3, 2026, the current official CodeWhale baseline is v0.8.50. It keeps `codewhale` as the canonical command/package, while the legacy `deepseek` / `deepseek-tui` binaries remain temporary deprecation shims scheduled to disappear in v0.9.0. | This is the setup delta most likely to break copy-pasted install instructions today. |
| What changed in Docker and manual-download safety guidance? | The current README and install docs treat `~/.codewhale` as the primary persistent home, and manual downloads should use CodeWhale asset names plus the published SHA-256 manifests. If you find older snippets that still mount `.deepseek`, treat them as compatibility-era examples rather than the primary path. | This prevents users from flattening two official-looking sources into one wrong Docker instruction. |
| What changed in config-home and credential setup? | The current README moves the primary user config file to `~/.codewhale/config.toml` and keeps `~/.deepseek/config.toml` only as a legacy fallback. It also documents `codewhale auth status` for checking whether the active key came from saved config, keyring, or DEEPSEEK_API_KEY, and `codewhale auth clear --provider deepseek` for rotation or cleanup. | This gives readers a reproducible way to debug 'wrong key', 'wrong account', or 'wrong config directory' problems. |
| What changed in TUI pricing and cost-tracking behavior? | The current README says DeepSeek's previous promotional discount was folded into a one-quarter base-rate adjustment on May 31, 2026, and that the TUI cost estimator already uses the current V4 Pro and V4 Flash rates. | This is the TUI-side pricing fact worth publishing because it affects cost estimates without changing the install flow. |
| What is the current default DeepSeek endpoint behavior? | The current README says the default DeepSeek Platform base URL is `https://api.deepseek.com/beta` so beta-gated API features work without extra setup. If you want the non-beta route, set `base_url = "https://api.deepseek.com"` explicitly. | This explains why two developers can see different provider behavior if one assumes the stable endpoint while the other uses the documented default. |
| Is DeepSeek TUI being renamed upstream? | Yes, and the rename is now official rather than speculative. The maintained project surfaces use CodeWhale as the product and command name, while the legacy `deepseek` binaries remain temporary deprecation shims that upstream still plans to remove in v0.9.0. | This is the clearest explanation for why two official-looking pages can show different command names. |
| Is DeepSeek TUI an official DeepSeek Inc. product? | No. DeepSeek TUI is an independent open-source project by developer Hunter Bown, licensed under MIT. It is not affiliated with DeepSeek Inc. It uses the public DeepSeek API just like any other third-party client. | This prevents confusion between the community tool and official DeepSeek products. |
| Does DeepSeek TUI run models locally? | No. It is an API client — it sends prompts to the DeepSeek cloud API over HTTPS. You need an internet connection and a DeepSeek API key. For local model execution, see the local deployment guide. | This is the most common misconception about terminal AI tools. |
| What does 'Pro does the big job, Flash does the small jobs' actually mean? | DeepSeek TUI's RLM feature uses deepseek-v4-pro as a coordinator (expensive, used briefly for strategy) and deepseek-v4-flash as parallel workers (cheap, used for bulk analysis). Pro decides what to do; Flash workers execute subtasks in parallel. This gives Pro-level reasoning at near-Flash pricing. | This is the core architecture insight that makes the tool cost-effective. |
| Can it replace Claude Code for my team? | It can replace parts of a Claude Code workflow for large-context, parallel-analysis, and cost-sensitive projects. For narrower tasks requiring the deepest reasoning on a single hard problem, Claude Code's model quality edge still matters. Many teams use both. | Honest capability comparison prevents over-selling and builds trust with technical readers. |
Start with the DeepSeek TUI developer website for the public product landing page, then use GitHub and the full guide for release notes and implementation details.
Open developer websiteThe complete tutorial: install, configure, understand the three work modes, use RLM parallel reasoning, master keyboard shortcuts, and compare with Claude Code.
Open the full guideDeepSeek TUI needs a DeepSeek API key. Official discounted keys are available here — same API, same context window, lower price.
View API plansTrying to decide between the DeepSeek and Claude ecosystems? Read the detailed model comparison covering coding, reasoning, and cost.
Compare modelsFAQ
The developer website is deepseek-tui.com. Treat it as the project landing page for DeepSeek TUI, while GitHub remains the primary source for code, releases, issues, and implementation documentation.
DeepSeek TUI is a terminal coding agent — you type prompts, and it can read your code, edit files, run commands, manage git, search the web, and dispatch parallel sub-agents. It's built specifically for DeepSeek V4's 1M-token context window, and its DeepSeek API route is often far cheaper per token than comparable Claude workflows.
The safest current answer is to treat `codewhale` as canonical: `npm install -g codewhale`, or the matching CodeWhale Cargo, Docker, Scoop, and manual-download paths from GitHub Releases. The older `deepseek-tui` path still works only as a temporary compatibility shim during the v0.8.50 transition.
Treat `~/.codewhale` as the primary config home because that is what the current README documents. But check the latest release page before copying Docker lines: the v0.8.49 release example still mounts `~/.deepseek`, so the safe explanation is that `.codewhale` is primary while `.deepseek` remains a live compatibility path.
Run `codewhale auth status`. The current README says it shows whether the active key came from saved config, keyring, or DEEPSEEK_API_KEY. If you need to remove a saved credential, use `codewhale auth clear --provider deepseek`. The legacy `deepseek auth ...` path still works only as a transition shim.
Not necessarily. The current README says the default DeepSeek Platform base URL is `https://api.deepseek.com/beta` so beta-gated features work out of the box. If you want the non-beta route, set `base_url = "https://api.deepseek.com"` explicitly.
Yes. Current official docs describe `codewhale doctor --json` for machine-readable health and `codewhale serve --http` for a localhost HTTP/SSE runtime API. The same runtime docs also list ACP and MCP stdio serve modes for tighter local integrations.
Plan mode is read-only exploration (safe for unfamiliar codebases). Agent mode proposes actions and waits for your approval (the daily driver). YOLO mode auto-approves everything (fast but risky — use only for well-defined batch tasks).
The RLM feature lets deepseek-v4-pro act as coordinator: it breaks a large task into subtasks and fans them out to 1–16 deepseek-v4-flash workers that run in parallel. Pro is used briefly for strategy; Flash handles the bulk work cheaply.
Yes. The UI is localized in English, Japanese, Simplified Chinese, and Brazilian Portuguese, with automatic detection.