of MiniMax M2.7's tool calls fail on NovitaAI (fp8).
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 | Groq# | 0.32% | 2.1k | $0.60 / $1.80 | 311 | 97.6% |
| 2 | MiniMax# | 1.76% | 16k | $0.30 / $1.20 | 38 | 99.4% |
| 3 | AtlasCloudfp8# | 1.93% | 2.5k | $0.30 / $1.20 | 49 | 98.8% |
| 4 | MiniMaxhighspeed# | 2.18% | 1.3k | $0.60 / $2.40 | 43 | 94.8% |
| 5 | GMICloudfp8# | 3.22% | 7.4k | $0.21 / $0.84 | 46 | 98.6% |
| 6 | NovitaAIfp8# | 3.94% | 9.9k | $0.27 / $1.08 | 28 | 99.5% |
Recommended OpenRouter settings for MiniMax M2.7
{
"provider": {
"order": [
"groq",
"minimax",
"atlas-cloud/fp8"
],
"ignore": [
"gmicloud/fp8",
"novita/fp8"
]
}
}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 NovitaAI (fp8) as on Groq, its best provider.
broken tool calls a day across its 5 providers.