feat: add nvidia/google/gemma-4-31b-it

[guillaumegay13]

✨ What changed

• Adds google/gemma-4-31b-it (nvidia) to the catalog, params cloned from nvidia/deepseek-v4-flash-0731.yaml.
• Hosted serving: the model is developed by google (OpenRouter: google/gemma-4-31b-it); this entry documents nvidia's serving of it, probed against nvidia's endpoint.

💭 Why

The provider serves it but the catalog doesn't list it. Param surfaces differ per serving provider, so each host gets its own probed entry (models.dev-style).

📝 Notes

• Liveness ✅ only: the model answers on its real endpoint; unverified params are listed in the evidence table below.
• Draft PR, auto-proposed by the modelparams agent.

Param verification evidence

param	check	ok	detail
(baseline)	accepted	✅	1-shot answers 200
temperature	min=0	➖	network/timeout: AbortError
temperature	max=1	➖	network/timeout: AbortError
top_p	max=1	➖	network/timeout: AbortError
top_p	range policed	✅	top_p=2 rejected
max_tokens	min=1	➖	network/timeout: AbortError
max_tokens	max=16384	➖	too large for a non-streaming probe — upper bound from docs
frequency_penalty	min=-2	➖	network/timeout: AbortError
frequency_penalty	max=2	➖	network/timeout: AbortError
presence_penalty	min=-2	➖	network/timeout: AbortError
presence_penalty	max=2	✅
seed	min=0	➖	network/timeout: AbortError
seed	max=18446744073709552000	✅
seed	range policed	❌	seed=36893488147419103000 accepted — declared max 18446744073709552000 may be too low or unenforced
stop	declared	➖	type string has no probe — value carried from sibling/docs, not verified

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated
modelparams.dev	Ready	Preview	Sep 7, 2026 6:41pm UTC