Devtoolwatch Boarddsh-our-free-model review
dsh-our-free-model is a dsh plugin that provides DeepSeek V4.1 Flash, Kimi K3 and other models without login, sign-up or API key.
TL;DR
dsh-our-free-model is a dsh plugin that adds a free model lane to dsh with no account or API key. It suits dsh users who want hosted models without configuration. It also checks which models are reachable from your own network and runs a local OpenAI-compatible and Anthropic-compatible gateway for other tools.
- 54.3kGitHub stars
- +13.9knew stars, week of Oct 25
- #1in Inference and training this week
dsh-our-free-model at a glance
- Category
- Inference and training
- Maintained by
- Nefert (individual, @Ebony-Vinyl on GitHub)
- License
- MIT
- Language
- JavaScript, CSS, TypeScript
- Repository
- github.com/Ebony-Vinyl/dsh-our-free-model
- Latest release
- v2.8.0 on GitHub, Nov 1, 2026
- First published
- Sep 24, 2026
What dsh-our-free-model does
- dsh-our-free-model adds models such as DeepSeek V4.1 Flash and Kimi K3 to the dsh model picker, with no login or API key.
- dsh-our-free-model probes availability from your machine's network exit and removes models the gateway refuses to route.
- dsh-our-free-model sends real reasoning effort levels or output token budgets upstream instead of prompt hints.
- dsh-our-free-model runs a local gateway with /v1/models, /v1/chat/completions, /v1/responses and /v1/messages endpoints for other local tools.
- dsh-our-free-model can register third-party providers with your own key, including OpenRouter, Groq, Ollama and LM Studio.
- dsh-our-free-model can chain models into named fallback or round-robin routes, exposed as combo:<name> virtual models.
- dsh-our-free-model shows a local usage dashboard and uploads no usage data.
How it works
dsh-our-free-model mounts as a dsh plugin with no kernel changes, build step or dependencies. Its free lanes connect directly to OpenCode's Zen gateway and Kilo AI's public gateway. A local forwarding port lets Claude Code, Codex, the OpenAI SDK, the Anthropic SDK or curl call the models. A standalone local service that does not require dsh is in development.
How to install and start using dsh-our-free-model
From npm (scoped package)
dsh plugin --profile web add @ebony-vinyl/[email protected]From a local directory
dsh plugin --profile web add /绝对路径/dsh-our-free-modelStandalone service from source
npm run start:standaloneRequirements
- A dsh installation. The standalone service is the only entry point that runs without dsh.
- Desktop (Electron) profiles must install the plugin through the desktop plugin manager, not the command line.
- The community macOS desktop package is Apple Silicon (arm64) only. Intel Macs must build from source.
First steps
- Restart the app once after installing the plugin.
- Open the model picker in the input box and choose a model from the Our Free Model group.
- Set reasoning strength with the Effort option in the same menu.
- To use the models from other tools, enable Settings → Our Free Model → local forwarding, then copy the base URL and generate a key.
Who dsh-our-free-model is for
- dsh users who want hosted models without creating accounts or managing API keys.
- Developers who want a local OpenAI- or Anthropic-compatible endpoint for tools like Claude Code or Codex.
- Users who want to combine free lanes and their own provider keys in one model list with fallback routes.
Limitations to know
- dsh-our-free-model's Kilo free pool may log prompts upstream to improve the service. Do not send sensitive content.
- dsh-our-free-model's unscoped npm package is published by a third party with modified files. Only @ebony-vinyl/dsh-our-free-model comes from this repository.
- dsh-our-free-model's LAN relay lets anyone with network access and the key use your quota. Enable it only on trusted networks.
- dsh-our-free-model's macOS build is unsigned and not notarized by Apple. The standalone service has no published release yet.
Is dsh-our-free-model growing? Usage data
In the week of Oct 25–31, 2026, dsh-our-free-model ranked #1 on the Devtoolwatch Board and #1 in Inference and training, with a momentum score of 100 out of 100.
Show the weekly numbers
| Week of | New stars |
|---|---|
| Aug 9, 2026 | – |
| Aug 16, 2026 | – |
| Aug 23, 2026 | – |
| Aug 30, 2026 | – |
| Sep 6, 2026 | – |
| Sep 13, 2026 | – |
| Sep 20, 2026 | 214 |
| Sep 27, 2026 | 456 |
| Oct 4, 2026 | 6.1k |
| Oct 11, 2026 | 14.8k |
| Oct 18, 2026 | 19.4k |
| Oct 25, 2026 | 13.9k |
The Board ranks tools by four signals each week: new stars, new stars for the repo's size, added downloads and download growth beyond the market. How the ranking works.
dsh-our-free-model alternatives
Other LLM inference and training tools on the Board in the week of Oct 25–31, 2026, by momentum:
| Rank | Tool | Stars | Downloads/wk |
|---|---|---|---|
| #2 | magpiemagpie is a local gateway and app that lets coding agents like Claude Code, Codex and Gemini CLI use any provider's model. | 26.9k | – |
| #3 | StrataStrata is a local inference engine and app that runs large open models like Qwen3.8-Flash-Next on consumer hardware with… | 37.1k | – |
| #4 | edge0edge0 is an open-source streaming inference framework that runs large sparse mixture-of-experts models on consumer hardware by streaming… | 8.9k | – |
| #5 | OmniRouteOmniRoute is an open-source AI gateway that routes requests across many model providers through one OpenAI-compatible endpoint, with… | 83.2k | 106k |
| #6 | CLIProxyAPICLIProxyAPI is a Go proxy server that exposes CLI coding accounts like Codex, Claude Code and Gemini CLI through OpenAI, Gemini and… | 57.1k | – |
| #7 | codex-chatgpt-webcodex-chatgpt-web is a launcher that lets Codex use the ChatGPT Web models on your account, including Pro, through browser automation. | 15.3k | – |
Recent dsh-our-free-model releases
- v2.8.0, Nov 1, 2026
- v2.8.0-macos-unofficial, Nov 1, 2026
- v2.7.4, Oct 31, 2026
- v2.7.4-macos-unofficial, Oct 31, 2026
- v2.7.3, Oct 30, 2026
dsh-our-free-model FAQ
Is dsh-our-free-model free and open source?
Yes. dsh-our-free-model's source code is on GitHub (Ebony-Vinyl/dsh-our-free-model) under the MIT license, so you can use it for free.
How do I install dsh-our-free-model?
Run dsh plugin --profile web add @ebony-vinyl/[email protected]. The install section above has the other options from the project's README.
Is dsh-our-free-model still maintained?
Yes. The Ebony-Vinyl/dsh-our-free-model repository was last updated on Nov 1, 2026, and the latest release, v2.8.0 on GitHub, came out on Nov 1, 2026.
How popular is dsh-our-free-model?
dsh-our-free-model has 54.3k GitHub stars as of Nov 1, 2026. It gained 13.9k new stars in the week of Oct 25–31, 2026, against a 12-week average of 9.1k a week. That made it #1 among LLM inference and training tools on the Devtoolwatch Board.
What are the best alternatives to dsh-our-free-model?
Other LLM inference and training tools on the Devtoolwatch Board in the week of Oct 25–31, 2026, by momentum: magpie (#2), Strata (#3), edge0 (#4), OmniRoute (#5), CLIProxyAPI (#6). The alternatives table above has their numbers.
Does dsh-our-free-model need an API key or account?
dsh-our-free-model needs no login, sign-up or API key for its free lanes. Its EAC channel is the exception: it requires GitHub authorization and a star on the repository before chats are allowed. The aggregation page can also use your own provider keys.
Where do dsh-our-free-model requests go?
dsh-our-free-model sends free lane requests directly to OpenCode's Zen gateway. Kilo channel requests go directly to Kilo AI's public gateway. Neither passes through a third-party relay.
Can other tools use dsh-our-free-model's models?
dsh-our-free-model can expose its models to other tools. Enable local forwarding in settings, then use the base URL and key. It supports GET /v1/models, POST /v1/chat/completions, POST /v1/responses and POST /v1/messages, and it generates configuration recipes for Claude Code, Codex and the SDKs.
Why is a model missing from the dsh-our-free-model picker?
dsh-our-free-model removes models the gateway explicitly refuses to route. It keeps them in a settings group with the reason. Models blocked in your region go into a region-limited group. Rerun the availability probe after changing your VPN state.
How does dsh-our-free-model update itself?
dsh-our-free-model upgrades from the settings page. It downloads, verifies SHA-256, backs up, replaces and hot-reloads the plugin. If any step fails, it rolls back to the previous version. Managed installs disable in-app upgrades.
Sources
dsh-our-free-model README badge
Maintainers can show the tool's weekly Board rank in their README:
[](https://index.devtoolwatch.com/tools/ebony-vinyl-dsh-our-free-model/)How this page is made: Devtoolwatch writes each review from the project's README, releases, package metadata and website, with an AI model, then checks every claim against the source it cites and drops what the sources don't support. The numbers come from Devtoolwatch's daily GitHub snapshots, GitHub's stargazer history, and the npm and PyPI download APIs. Spotted an error? Email [email protected].