of MiniMax M3.1 Flash's tool calls fail on Fireworks.
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 | Together# | 1.17% | 76k | $0.15 / $0.60 | 120 | 99.6% |
| 2 | Parasailfp8# | 1.37% | 56k | $0.15 / $0.60 | 157 | 99.7% |
| 3 | ModelRun [by Modular]fp4# | 1.42% | 17k | $0.15 / $0.60 | 157 | 99.8% |
| 4 | StreamLakefp8# | 1.71% | 1.2k | $0.14 / $0.54 | 54 | 98.5% |
| 5 | inference.netfp4# | 1.74% | 144k | $0.15 / $0.60 | 68 | 97.6% |
| 6 | NovitaAIfp16# | 2.05% | 17k | $0.15 / $0.60 | 78 | 99.8% |
| 7 | DigitalOcean# | 2.61% | 84k | $0.15 / $0.60 | 202 | 100.0% |
| 8 | SambaNova# | 2.62% | 1.5k | $0.06 / $0.24 | 45 | 99.1% |
| 9 | MiniMax# | 2.98% | 2.6M | $0.15 / $0.60 | 119 | 100.0% |
| 10 | GMICloudfp8# | 3.88% | 47k | $0.14 / $0.57 | 113 | 99.0% |
| 11 | Fireworks# | 11.02% | 1.4k | $0.15 / $0.60 | 118 | 99.8% |
{
"provider": {
"order": [
"together",
"parasail/fp8",
"modelrun/fp4"
],
"ignore": [
"gmicloud/fp8",
"fireworks"
]
}
}Point your agent at llms.txt
And which provider to use.
Releasing a model? Test it before launch.
of MiniMax M3.1 Flash's tool calls fail on Fireworks.
as often on Fireworks as on Together, its best provider.
broken tool calls a day across its 11 providers.