.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
Tencent · 5 providers · 4.7M tool calls a day
#ProviderBroken
tool calls
Tool calls
a day
$ in / out
per M
Tokens/sUptime
1Tencent Cloudfp8#1.46%4.6M$0.08 / $0.3356100.0%
2AtlasCloudfp8#1.63%3.9k$0.20 / $0.804299.7%
3GMICloudbf16#1.67%7.5k$0.14 / $0.584799.9%
4Phala#1.71%5.9k$0.15 / $0.6462100.0%
5NovitaAI#3.23%30k$0.14 / $0.5873100.0%
Recommended OpenRouter settings for Hy3
{
  "provider": {
    "order": [
      "tencent/fp8",
      "atlas-cloud/fp8",
      "gmicloud/bf16"
    ],
    "ignore": [
      "novita"
    ]
  }
}

Point your agent at llms.txt

Using Hy3?

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 provider3.23%

of Hy3's tool calls fail on NovitaAI.

Best to worst2×

as often on NovitaAI as on Tencent Cloud (fp8), its best provider.

Every day69k

broken tool calls a day across its 5 providers.