.TXT Serve models?→Release models?↓
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.

← All models
NVIDIA · 4 providers · 138k tool calls a day
#ProviderBroken
tool calls
Tool calls
a day
$ in / out
per M
Tokens/sUptime
1Darkbloomint4#0.01%3.9k$0.03 / $0.126899.7%
2io.net#3.18%9.3k$0.05 / $0.134099.3%
3CoreWeavebf16#7.94%103k$0.07 / $0.20252100.0%
4DeepInfrabf16#9.96%21k$0.06 / $0.1616499.7%
Recommended OpenRouter settings for Nemotron 3.5 Lightning
{
  "provider": {
    "order": [
      "darkbloom/int4"
    ],
    "ignore": [
      "io-net",
      "coreweave/bf16",
      "deepinfra/bf16"
    ]
  }
}

Point your agent at llms.txt

Using Nemotron 3.5 Lightning?

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.

Worst provider9.96%

of Nemotron 3.5 Lightning's tool calls fail on DeepInfra (bf16).

Best to worst100×

as often on DeepInfra (bf16) as on Darkbloom (int4), its best provider.

Every day11k

broken tool calls a day across its 4 providers.