of DeepSeek V4 Flash Vision Exp's tool calls fail on DeepInfra (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 | GMICloudfp8# | 0.58% | 5.0k | $0.44 / $1.32 | 86 | 99.9% |
| 2 | SiliconFlowfp8# | 0.58% | 18k | $0.44 / $1.32 | 141 | 99.9% |
| 3 | DeepInfrafp8# | 1.92% | 83k | $0.22 / $0.65 | 69 | 100.0% |
{
"provider": {
"order": [
"gmicloud/fp8",
"siliconflow/fp8",
"deepinfra/fp8"
],
"ignore": []
}
}Point your agent at llms.txt
And which provider to use.
Releasing a model? Test it before launch.
of DeepSeek V4 Flash Vision Exp's tool calls fail on DeepInfra (fp8).
as often on DeepInfra (fp8) as on GMICloud (fp8), its best provider.
broken tool calls a day across its 3 providers.