of Hy4 preview's tool calls fail on SiliconFlow (fp8).
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# | 0.10% | 90k | $0.79 / $2.38 | 39 | 99.9% |
| 2 | NovitaAIfp8# | 0.15% | 238k | $0.83 / $2.50 | 42 | 100.0% |
| 3 | Tencent Cloudfp8# | 0.16% | 10.7M | $0.75 / $2.25 | 46 | 99.9% |
| 4 | Cohere# | 0.17% | 39k | $0.83 / $2.50 | 76 | 99.0% |
| 5 | AtlasCloudfp8# | 0.35% | 13k | $0.83 / $2.50 | 37 | 99.9% |
| 6 | SiliconFlowfp8# | 0.77% | 165k | $0.83 / $2.50 | 32 | 99.9% |
{
"provider": {
"order": [
"deepinfra/fp4",
"novita/fp8",
"tencent/fp8"
],
"ignore": []
}
}Point your agent at llms.txt
And which provider to use.
Releasing a model? Test it before launch.
of Hy4 preview's tool calls fail on SiliconFlow (fp8).
as often on SiliconFlow (fp8) as on DeepInfra (fp4), its best provider.
broken tool calls a day across its 6 providers.