of Nemotron 3 Ultra's tool calls fail on Baseten (fp4).
Updated October 29, 2026
Tool-call index
Not all models are served equally by all providers. On a typical model, the worst provider breaks tool calls 19× as often as the best. Find the best one for your agents.
| # | Provider | Broken tool calls | Tool calls a day | $ in / out per M | Tokens/s | Uptime |
|---|---|---|---|---|---|---|
| 1 | DeepInfrafp4/flex# | 0.17% | 1.6k | $0.40 / $1.76 | — | 99.5% |
| 2 | Venicefp8# | 0.19% | 11k | $0.62 / $3.12 | 94 | 81.6% |
| 3 | DeepInfrafp4# | 1.07% | 7.7k | $0.50 / $2.20 | 88 | 99.9% |
| 4 | Basetenfp4# | 3.58% | 19k | $0.60 / $2.40 | 105 | 94.0% |
Recommended OpenRouter settings for Nemotron 3 Ultra
{
"provider": {
"order": [
"deepinfra/fp4/flex",
"venice/fp8",
"deepinfra/fp4"
],
"ignore": [
"baseten/fp4"
]
}
}Point your agent at llms.txt
Get updates when its successor drops
And which provider to use.
For model makers
Broken tool calls carry your model's name
Releasing a model? Test it before launch.
as often on Baseten (fp4) as on DeepInfra (fp4/flex), its best provider.
broken tool calls a day across its 3 providers.