of Hy3's tool calls fail on NovitaAI.
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 | Tencent Cloudfp8# | 1.46% | 4.6M | $0.08 / $0.33 | 56 | 100.0% |
| 2 | AtlasCloudfp8# | 1.63% | 3.9k | $0.20 / $0.80 | 42 | 99.7% |
| 3 | GMICloudbf16# | 1.67% | 7.5k | $0.14 / $0.58 | 47 | 99.9% |
| 4 | Phala# | 1.71% | 5.9k | $0.15 / $0.64 | 62 | 100.0% |
| 5 | NovitaAI# | 3.23% | 30k | $0.14 / $0.58 | 73 | 100.0% |
{
"provider": {
"order": [
"tencent/fp8",
"atlas-cloud/fp8",
"gmicloud/bf16"
],
"ignore": [
"novita"
]
}
}Point your agent at llms.txt
And which provider to use.
Releasing a model? Test it before launch.
of Hy3's tool calls fail on NovitaAI.
as often on NovitaAI as on Tencent Cloud (fp8), its best provider.
broken tool calls a day across its 5 providers.