of Muse Spark Open's tool calls fail on Modal.
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 | Nebius Token Factoryfp4# | 0.07% | 13k | $1.25 / $4.25 | 76 | 95.1% |
| 2 | Fireworks# | 0.32% | 13k | $1.25 / $4.25 | 76 | 99.1% |
| 3 | Together# | 0.38% | 34k | $1.25 / $4.25 | 92 | 99.4% |
| 4 | Makorafp4# | 1.61% | 38k | $1.25 / $4.25 | 169 | 100.0% |
| 5 | Basetenfp4# | 2.17% | 1.3k | $1.25 / $4.25 | 175 | 100.0% |
| 6 | Modal# | 3.26% | 7.9k | $1.25 / $4.25 | 75 | 99.3% |
Recommended OpenRouter settings for Muse Spark Open
{
"provider": {
"order": [
"nebius/fp4",
"fireworks",
"together"
],
"ignore": [
"modal"
]
}
}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 Modal as on Nebius Token Factory (fp4), its best provider.
broken tool calls a day across its 6 providers.