of DeepSeek V3.2's tool calls fail on GMICloud (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 | SiliconFlowfp8# | 0.60% | 27k | $0.26 / $0.80 | 19 | 99.9% |
| 2 | DeepInfrafp4# | 0.65% | 67k | $0.26 / $0.38 | 35 | 99.5% |
| 3 | Phala# | 0.76% | 3.0k | $1.00 / $1.00 | 30 | 100.0% |
| 4 | GMICloudfp8# | 1.61% | 32k | $0.21 / $0.31 | 49 | 99.9% |
{
"provider": {
"order": [
"siliconflow/fp8",
"deepinfra/fp4",
"phala"
],
"ignore": []
}
}Point your agent at llms.txt
And which provider to use.
Releasing a model? Test it before launch.
of DeepSeek V3.2's tool calls fail on GMICloud (fp8).
as often on GMICloud (fp8) as on SiliconFlow (fp8), its best provider.
broken tool calls a day across its 4 providers.