of GLM 4.7's tool calls fail on DeepInfra (fp4).
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 | Z.aifp4# | 0.93% | 1.4k | $0.60 / $2.20 | 24 | 99.9% |
| 2 | NovitaAIfp8# | 1.04% | 2.0k | $0.54 / $1.98 | 23 | 99.9% |
| 3 | DeepInfrafp4# | 2.22% | 2.3k | $0.40 / $1.75 | 19 | 98.4% |
Recommended OpenRouter settings for GLM 4.7
{
"provider": {
"order": [
"z-ai/fp4",
"novita/fp8",
"deepinfra/fp4"
],
"ignore": []
}
}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 DeepInfra (fp4) as on Z.ai (fp4), its best provider.
broken tool calls a day across its 3 providers.