of Nemotron 3.5 Lightning's tool calls fail on DeepInfra (bf16).
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 | Darkbloomint4# | 0.01% | 3.9k | $0.03 / $0.12 | 68 | 99.7% |
| 2 | io.net# | 3.18% | 9.3k | $0.05 / $0.13 | 40 | 99.3% |
| 3 | CoreWeavebf16# | 7.94% | 103k | $0.07 / $0.20 | 252 | 100.0% |
| 4 | DeepInfrabf16# | 9.96% | 21k | $0.06 / $0.16 | 164 | 99.7% |
{
"provider": {
"order": [
"darkbloom/int4"
],
"ignore": [
"io-net",
"coreweave/bf16",
"deepinfra/bf16"
]
}
}Point your agent at llms.txt
And which provider to use.
Releasing a model? Test it before launch.
of Nemotron 3.5 Lightning's tool calls fail on DeepInfra (bf16).
as often on DeepInfra (bf16) as on Darkbloom (int4), its best provider.
broken tool calls a day across its 4 providers.