of Qwen3.8 2.4T A95B's tool calls fail on Together.
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 | SiliconFlowfp8# | 0.19% | 9.4k | $2.00 / $6.00 | 35 | 100.0% |
| 2 | Venice# | 0.22% | 4.1k | $2.00 / $6.00 | 124 | 99.2% |
| 3 | Alibaba Cloud Int.# | 1.33% | 3.3k | $2.00 / $6.00 | 34 | 100.0% |
| 4 | NovitaAI# | 3.11% | 4.5k | $2.00 / $6.00 | 34 | 99.9% |
| 5 | Together# | 4.19% | 12k | $2.00 / $6.00 | 104 | 99.9% |
Recommended OpenRouter settings for Qwen3.8 2.4T A95B
{
"provider": {
"order": [
"siliconflow/fp8",
"venice",
"alibaba"
],
"ignore": [
"novita",
"together"
]
}
}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 Together as on SiliconFlow (fp8), its best provider.
broken tool calls a day across its 5 providers.