.TXT Serve models?→Release models?↓
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.

← All models
Z.ai · 5 providers · 25k tool calls a day
#ProviderBroken
tool calls
Tool calls
a day
$ in / out
per M
Tokens/sUptime
1GMICloudfp8#0.74%3.8k$0.60 / $1.926499.9%
2StreamLakefp8#0.89%13k$0.60 / $1.9260100.0%
3Z.aifp8#2.22%3.4k$1.00 / $3.204399.6%
4SiliconFlowfp8#2.24%3.6k$0.95 / $2.554899.9%
5Amazon Bedrock#3.13%1.0k$1.00 / $3.2011399.6%
Recommended OpenRouter settings for GLM 5
{
  "provider": {
    "order": [
      "gmicloud/fp8",
      "streamlake/fp8",
      "z-ai/fp8"
    ],
    "ignore": [
      "amazon-bedrock"
    ]
  }
}

Point your agent at llms.txt

Using GLM 5?

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.

Worst provider3.13%

of GLM 5's tool calls fail on Amazon Bedrock.

Best to worst4×

as often on Amazon Bedrock as on GMICloud (fp8), its best provider.

Every day336

broken tool calls a day across its 5 providers.