display.dev for Llama
You run Llama. display.dev is where its output lands – at a permanent URL, behind your company login when you want it. Llama is open-weight, so it runs on your hardware with no vendor in the loop. That's also why there's no hosted place to put the HTML and Markdown it produces, and no account your viewers already have. display.dev is that place. One command, permanent URL, gated by your company's Google or Microsoft login.
Llama runs on your terms. Output sharing doesn't follow.
You chose Llama to keep data on your infrastructure, skip the per-token vendor bill, and avoid lock-in to one API. The model runs – on Ollama, vLLM, llama.cpp, or your own serving stack – and it writes real output: analyses, dashboards, reports, internal docs.
Then someone has to read it. And because there's no vendor behind Llama, there's no "share with my org" button and no account your teammate can sign into. The output becomes an email attachment or a Slack paste that loses its interactivity and stops being a stable reference.
display.dev gives Llama's output the home that an open-weight model doesn't ship with.
From Llama output to a company URL
Publish a file Llama wrote:
dsp publish ./report.html --name "market-analysis"Publish from a script around your serving stack:
python run_llama.py --out ./report.html # Ollama / vLLM / llama.cpp under the hood
dsp publish ./report.html --name "report-$(date +%Y-%m-%d)"Publish as an agent tool call (MCP):
{
"name": "publish",
"arguments": { "content": "<html>...", "name": "llama-output", "visibility": "company" }
}The URL is permanent and authenticated. Paste it anywhere. The viewer signs in once with their company email and sees the full rendered result.
Viewers sign in with their work email. Nothing else.
Running Llama yourself means there's no vendor account to share through, and no account your viewers already hold. That's the trade you made on purpose.
display.dev is vendor-independent. Viewers sign in with the Google or Microsoft email they already use for work. No display.dev account to create, no model account, nothing to install. They click the link and read the page.
The best model changes. The home doesn't.
Today it's Llama. Next quarter you might add a Qwen fine-tune or swap a 70B for something newer. display.dev sits above the model – rotate freely, and everything you published keeps its URL, versions, and comment threads.
Pricing
Try it. No credit card.
- Included: 10 gated artifacts
- Included: Unlimited public artifacts*
- Included: 50MB storage
- Not included: Version history
- Not included: Google + Microsoft SSO
- Not included: Private artifacts
- Not included: Audit logs
display.dev branded
Individuals. Unlimited gated sharing.
- Included: Unlimited gated artifacts
- Included: Unlimited public artifacts
- Included: 1GB storage
- Included: 10 versions
- Not included: Google + Microsoft SSO
- Not included: Private artifacts
- Not included: Audit logs
For teams that need company auth.
- Included: Unlimited gated artifacts
- Included: Unlimited public artifacts
- Included: 25GB storage
- Included: 50 versions
- Included: Google + Microsoft SSO
- Included: Private artifacts
- Included: 90 days audit logs
For compliance-driven organizations.
From €499/mo
- Included: Unlimited gated artifacts
- Included: Unlimited public artifacts
- Included: Custom storage
- Included: Unlimited versions
- Included: Google + Microsoft SSO
- Included: Private artifacts
- Included: 365 days audit logs
Features
Viewers click a link and sign in with their Google or Microsoft account, or a one-time password. No app to install. No account to create. No IT ticket.
Inline comments on every artifact. Your agent reads them via MCP, fetches the current version, republishes with short_id and base_version, and resolves the thread. The artifact stays a living document, not a one-shot screenshot.
dsp publish ./file.html from your terminal, or one MCP tool call. No git repo, no deploy pipeline, no project to configure.
Every artifact gets a URL that keeps working. Share in Slack, link in Notion, paste in email. It still works six months later.
No per-seat pricing at any tier. Share with your PM, exec, legal team, or designer for the same flat price.
Llama and any other open-weight model – plus Claude Code, Cursor, Codex, or your own scripts.
Common questions.
Which Llama versions does this work with?
All of them, and any runtime. display.dev publishes any HTML or Markdown file on disk – it never sees the model. Llama 3, Llama 4, a fine-tune, served via Ollama, vLLM, or llama.cpp: if it writes a file, dsp publish works.
Do viewers need anything installed or any AI account?
No. Viewers sign in with their company Google or Microsoft email. No display.dev account, no model account, nothing to install on their side.
Does my Llama deployment leave my infrastructure?
No. Only the artifact you explicitly publish leaves. Your weights, serving stack, and data stay on your own hardware.
Can my pipeline publish automatically after inference?
Yes. Add dsp publish to the end of the script, or wire display.dev's MCP/REST API into your agent so it publishes its own output and returns the URL.
What if I switch from Llama to another model?
Nothing moves. display.dev is independent of what produced the output, so every URL, version, and comment thread stays put.
Publish your first artifact in 15 seconds.
Free tier. No credit card. One-time password auth on free, Google + Microsoft SSO on Pro (€49/month flat).