of Qwen3.5 397B A17B's tool calls fail on Phala.
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.
| # | Provider | Broken tool calls | Tool calls a day | $ in / out per M | Tokens/s | Uptime |
|---|---|---|---|---|---|---|
| 1 | Alibaba Cloud Int.# | 0.58% | 6.6k | $0.39 / $2.34 | 58 | 99.8% |
| 2 | NovitaAI# | 0.72% | 2.8k | $0.60 / $3.60 | 55 | 98.1% |
| 3 | DeepInfrafp8# | 1.13% | 9.5k | $0.45 / $3.00 | 48 | 99.7% |
| 4 | Venice# | 1.27% | 1.2k | $0.75 / $4.50 | 53 | 96.7% |
| 5 | AtlasCloudfp8# | 1.55% | 1.6k | $0.55 / $3.50 | 56 | 97.8% |
| 6 | Parasailfp8# | 2.21% | 9.1k | $0.50 / $3.60 | 100 | 99.9% |
| 7 | Phala# | 11.30% | 6.1k | $0.55 / $3.50 | 46 | 98.1% |
Recommended OpenRouter settings for Qwen3.5 397B A17B
{
"provider": {
"order": [
"alibaba",
"novita",
"deepinfra/fp8"
],
"ignore": [
"phala"
]
}
}Point your agent at llms.txt
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.
as often on Phala as on Alibaba Cloud Int., its best provider.
broken tool calls a day across its 7 providers.