of Qwen3.6 35B A3B'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 | AkashMLfp8# | 1.63% | 66k | $0.10 / $0.90 | 63 | 100.0% |
| 2 | Parasailfp8# | 1.75% | 96k | $0.10 / $0.90 | 98 | 99.9% |
| 3 | DeepInfrafp8# | 2.01% | 24k | $0.10 / $0.95 | 28 | 99.0% |
| 4 | AtlasCloudfp8# | 2.46% | 9.3k | $0.25 / $1.25 | 118 | 81.5% |
| 5 | DekaLLM# | 3.36% | 12k | $0.10 / $1.00 | 129 | 98.2% |
| 6 | Phala# | 5.75% | 8.0k | $0.20 / $1.27 | 117 | 99.1% |
Recommended OpenRouter settings for Qwen3.6 35B A3B
{
"provider": {
"order": [
"akashml/fp8",
"parasail/fp8",
"deepinfra/fp8"
],
"ignore": [
"dekallm",
"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 AkashML (fp8), its best provider.
broken tool calls a day across its 6 providers.