How much does the Lyria API cost on varg?

Lyria 3.5 costs from $0.10 per run on varg. Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. For the exact price of a request before you run it, send the same body to POST https://api.varg.ai/v2/estimate.

How long do Lyria 3.5 requests take?

Typically about 2 min, by the catalog's estimate for its fastest route. The API answers at once with a job id, so nothing waits on an open connection while it runs.

How do I call the Lyria API?

Send POST https://api.varg.ai/v2/tools/music/call with the header "Authorization: Bearer $VARG_API_KEY" and a JSON body that includes "model", for example "model": "lyria_3_5". The call answers 202 with a job right away. Poll GET https://api.varg.ai/v2/jobs/{id} until "status" is "completed", then read output.outputs[0].url, or pass options.webhook_url to be called back.

Can I use Lyria from Claude, ChatGPT or Cursor?

Yes. Add the varg MCP server (https://mcp.varg.ai/mcp) to Claude, ChatGPT, Cursor or any other MCP client and sign in with varg, with no API key to paste. The agent runs a model with call_tool, passing tool "music" and the model id, for example "model": "lyria_3_5".

1 model · music

Lyria API

Lyria is an AI music model made by Google. varg runs it on one API key as Lyria 3.5. It covers music; it returns audio.

Price: From $0.10 per run
Made by: Google
Flagship id: lyria_3_5

Lyria 3.5 runs on one varg API key and one credit balance, the same as every other model here. You pay the provider's price, with no markup.

POST /v2/tools/music/call

curl -X POST https://api.varg.ai/v2/tools/music/call \
  -H "Authorization: Bearer $VARG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "lyria_3_5",
  "prompt": "A 90-second synthwave track with a female vocal hook about city lights. [0:00-0:15] Intro: arpeggiated synths. [0:15-0:45] Verse. [0:45-1:30] Chorus.",
  "duration": 5
}'

Try Lyria 3.5 in the Playground Get an API key

Lyria models and prices

Lyria on varg starts from $0.10 per run (Lyria 3.5). Prices are in US dollars and are the provider's own, with no markup. A "from" price is the cheapest request the catalog states for that model; each model's page has every rate and input. The descriptions are the catalog's own, shortened.

Lyria models on varg
Model	Catalog description	Takes	Price	Typical time
Lyria 3.5`lyria_3_5`	Lyria 3.5 by Google. Full songs up to about 3 minutes with vocals and lyrics, or instrumentals; set length and structure in the prompt.	Music	From $0.10 per run	~2 min

Call the Lyria API

The call below runs Lyria 3.5.

REST

POST https://api.varg.ai/v2/tools/music/call with Authorization: Bearer $VARG_API_KEY. It answers 202 with a job right away; poll GET /v2/jobs/{id} until its status is completed, then read output.outputs[0].url.

POST /v2/tools/music/call

curl -X POST https://api.varg.ai/v2/tools/music/call \
  -H "Authorization: Bearer $VARG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "lyria_3_5",
  "prompt": "A 90-second synthwave track with a female vocal hook about city lights. [0:00-0:15] Intro: arpeggiated synths. [0:15-0:45] Verse. [0:45-1:30] Chorus.",
  "duration": 5
}'

From Claude, ChatGPT or Cursor (MCP)

The varg MCP server, https://mcp.varg.ai/mcp, runs Lyria 3.5 with call_tool. Sign in with varg, no API key to paste. How to connect it

Claude Code

claude mcp add --transport http varg https://mcp.varg.ai/mcp

call_tool

{
  "tool": "music",
  "input": {
    "model": "lyria_3_5",
    "prompt": "A 90-second synthwave track with a female vocal hook about city lights. [0:00-0:15] Intro: arpeggiated synths. [0:15-0:45] Verse. [0:45-1:30] Chorus.",
    "duration": 5
  },
  "wait": true
}

From a terminal (CLI)

vargai is the varg command line: every tool of the MCP server is a command. Install and log in

vargai

curl -fsSL https://varg.ai/install | sh
vargai call_tool --tool music '{"model":"lyria_3_5","prompt":"A 90-second synthwave track with a female vocal hook about city lights. [0:00-0:15] Intro: arpeggiated synths. [0:15-0:45] Verse. [0:45-1:30] Chorus.","duration":5}'

How billing works

Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. varg's fee is on the top-up, not on the run: 5.5% of the credits you buy ($0.80 at the least), or 8% for a team workspace. Pricing

How to use Lyria

Step-by-step pages on varg how to.

Lyria API: questions

How much does the Lyria API cost on varg?: Lyria 3.5 costs from $0.10 per run on varg. Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. For the exact price of a request before you run it, send the same body to POST https://api.varg.ai/v2/estimate.
How long do Lyria 3.5 requests take?: Typically about 2 min, by the catalog's estimate for its fastest route. The API answers at once with a job id, so nothing waits on an open connection while it runs.
How do I call the Lyria API?: Send POST https://api.varg.ai/v2/tools/music/call with the header "Authorization: Bearer $VARG_API_KEY" and a JSON body that includes "model", for example "model": "lyria_3_5". The call answers 202 with a job right away. Poll GET https://api.varg.ai/v2/jobs/{id} until "status" is "completed", then read output.outputs[0].url, or pass options.webhook_url to be called back.
Can I use Lyria from Claude, ChatGPT or Cursor?: Yes. Add the varg MCP server (https://mcp.varg.ai/mcp) to Claude, ChatGPT, Cursor or any other MCP client and sign in with varg, with no API key to paste. The agent runs a model with call_tool, passing tool "music" and the model id, for example "model": "lyria_3_5".

More model APIs

Same API key, same request shape: change the model string to switch.

All models

For AI agents: each model above has its full spec as Markdown at varg.ai/models/lyria_3_5.md (swap the id), and every model is listed in varg.ai/models/llms.txt.