GoModel
Hacker ApprovedRanked 3 of 8 LLM gateways by recommenders
Self-hosted AI gateway people praise for its lightweight footprint, request debugging dashboard, and virtual models that swap backing models without reconfiguring tools. Some critics doubt its benchmarks.
Self-hosted AI gateway people praise for its lightweight footprint, request debugging dashboard, and virtual models that swap backing models without reconfiguring tools. Some critics doubt its benchmarks.
15 people gave an opinion
- recommend it
- 13
- criticize it
- 2
- approval share
- 87%
Recommended in 6 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: not recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: recommended (month in progress)
Why it carries the badge
- 13 people recommend itNeeds 10 or more, met.
- 6.5 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 6 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Virtual models swap backing models easily
“I use GoModel and its amazing. My favorite features are virtual model, the support for arbitrary request labels, and the nice dashboads / ui.”
Comment from 19 Oct 2026 in “If you don't run your own LLM proxy, how do you know whats going on?” “If you were to use a gateway like GoModel then you could use Virtual Models to load balance across the subscriptions.”
Comment from 7 Oct 2026 in “Mistral Large 4” “my favorite feature is the virtual models, stable name, I can swap out the backing model(s)”
Comment from 25 Sep 2026 in “Ollaya – Ollama for open-source, Jev-style decision models” - Comment from 21 Oct 2026 in “Compromised LiteLLM 1.107.0 on PyPI Installs a Credential Stealer and Backdoor”
- Comment from 9 Jul 2026 in “Why the Next Era of AI Is About Infrastructure, Not Just Models”
- Comment from 20 Jul 2026 in “Ask HN: Run Kimi in Claude Code?”
Keeps keys off vendors; self-hosted
“I would recommend running your own gateway instead of uploading keys to a vendor”
Comment from 18 Oct 2026 in “OpenCode Hacked: User credentials leaked” “get yourself a gateway like GoModel and put all your credentials there”
Comment from 20 Oct 2026 in “Ask HN: How to get the most intelligence out of your agents?” “Run a gateway like GoModel instead of uploading your keys to a vendor”
Comment from 18 Oct 2026 in “OpenCode Hacked: User credentials leaked” - Comment from 18 Oct 2026 in “OpenCode Hacked: User credentials leaked”
- Comment from 21 Oct 2026 in “Launch HN: Alter (YC S25) – Access control for multi-user agents”
- Comment from 18 Oct 2026 in “OpenCode Hacked: User credentials leaked”
Lightweight and fast
“it looks like GoModel is the fastest and most lightweight open-source (self-hosted) AI gateway on the market”
Comment from 14 Jul 2026 in “Ask HN: What Are You Working On? (July 2026)” “Memory usage is a much better metric and GoModel wins here.”
Comment from 26 Jul 2026 in “How good is your AI Gateway?” “It consumes ~60x less resources and is more reliable”
Comment from 14 Jul 2026 on Hacker News - Comment from 21 Oct 2026 in “Compromised LiteLLM 1.107.0 on PyPI Installs a Credential Stealer and Backdoor”
- Comment from 22 Apr 2026 in “Show HN: GoModel – an open-source AI gateway in Go; 44x lighter than LiteLLM”
Request visibility and debugging
“I use GoModel and its amazing. My favorite features are virtual model, the support for arbitrary request labels, and the nice dashboads / ui.”
Comment from 19 Oct 2026 in “If you don't run your own LLM proxy, how do you know whats going on?” “IMO GoModel is more convenient for debugging and for seeing how your request flows through different layers of AI Gateways”
Comment from 21 Apr 2026 in “Show HN: GoModel – an open-source AI gateway in Go; 44x lighter than LiteLLM” “AI interaction visualization that makes debugging individual request/response flows much easier.”
Comment from 22 Apr 2026 in “Show HN: GoModel – an open-source AI gateway in Go; 44x lighter than LiteLLM” - Comment from 16 Oct 2026 in “LLM says something, my tool track if it followed its promise on tools”
What people warn about
Each mark is one comment
Doubts about benchmarks and docs
“I see some red flags in the docs/benchmarks, but I could be wrong in my judgement here.”
Comment from 21 Apr 2026 in “Show HN: GoModel – an open-source AI gateway in Go; 44x lighter than LiteLLM” “It’s a heavily vibe coded project with only proxy with terrible benchmarks design.”
Comment from 21 Apr 2026 in “Show HN: GoModel – an open-source AI gateway in Go; 44x lighter than LiteLLM”
Other LLM gateways people recommend
The four most recommended other LLM gateways, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| LiteLLM | 72 | 94 | 43% | 12 | — | — |
| Bifrost by Maxim | 17 | 6 | 74% | 10 | — | Approved |
| GoModelThis page | 13 | 2 | 87% | 6 | — | Approved |
| Claude Code Router | 11 | 3 | 79% | 5 | — | Approved |
| CLIProxyAPI | 7 | 1 | 88% | 5 | — | — |
What people said
34 of the 37 comments that mention it, newest first. Each links to the original comment.
“planning to use GoModel instead”
“GoModel's virtual models have been super helpful for testing out new open weights.”
“Run your own gateway behind a firewall / vpn.”
“20x faster and less "targeted" LiteLLM alternative”
“all providers are built in”
“get yourself a gateway like GoModel and put all your credentials there”
“I use GoModel and its amazing. My favorite features are virtual model, the support for arbitrary request labels, and the nice dashboads / ui.”
“Use a gateway like LiteLLM or GoModel, don't upload keys to a vendor”
“I would recommend running your own gateway instead of uploading keys to a vendor”
“Run a gateway like GoModel instead of uploading your keys to a vendor”
“don't upload keys to a vendor”
“We use GoModel for the gateway and visibility”
“my gateway of choice, also very good”
“If you were to use a gateway like GoModel then you could use Virtual Models to load balance across the subscriptions.”
“my favorite feature is the virtual models, stable name, I can swap out the backing model(s)”
“Memory usage is a much better metric and GoModel wins here.”
“a great gateway where you can swap out models without touching CC”
“It consumes ~60x less resources and is more reliable”
“I've written one - GoModel.”
“it looks like GoModel is the fastest and most lightweight open-source (self-hosted) AI gateway on the market”
“I can swap out models or quants and my tools do not need to be reconfigured.”
“AI interaction visualization that makes debugging individual request/response flows much easier.”
“Really slick and lightweight!”
“this looks super nice. I do like the 'compact' feel of this”
“GoModel is designed to be flexible. If you add an extra field, it tries to pass it through in the appropriate place”
“it's nice that it supports different providers”
“I see some red flags in the docs/benchmarks, but I could be wrong in my judgement here.”
“It’s a heavily vibe coded project with only proxy with terrible benchmarks design.”
“Looks nice, thanks for open sourcing and sharing.”
“something like this project would be a lot simpler than manually configuring API clients for each model in each project”
“I don't see any significant advantage over mature routers like Bifrost.”
“IMO GoModel is more convenient for debugging and for seeing how your request flows through different layers of AI Gateways”
“kudos for the project, we need more alternatives in compiled languages”
“It's open-source and progressing really fast!”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.