of Qwen3 30B A3B Instruct 2507'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 | Nebius Token Factoryfp8# | 2.89% | 25k | $0.10 / $0.30 | 158 | 99.4% |
| 2 | SiliconFlowfp8# | 4.38% | 22k | $0.09 / $0.30 | 27 | 99.3% |
Also ignored, under 1,000 tool calls a day: DekaLLM 7.88%.
{
"provider": {
"order": [
"nebius/fp8"
],
"ignore": [
"siliconflow/fp8",
"dekallm"
]
}
}Point your agent at llms.txt
And which provider to use.
Releasing a model? Test it before launch.
of Qwen3 30B A3B Instruct 2507's tool calls fail on SiliconFlow (fp8).
as often on SiliconFlow (fp8) as on Nebius Token Factory (fp8), its best provider.
broken tool calls a day across its 2 providers.