Structured-output index

The same model breaks your pipeline's structured outputs 15× more often on some inference providers than on others. Find the best one for your pipelines.

Give this to your agent ↓

providers.dottxt.ai/llms.txt

← All models

MiniMax · 3 providers · 96k structured outputs a day

#	Provider		Structured outputs a day	$ in / out per M	Tokens/s	Uptime
1	CoreWeavefp4#	0.61%	54k	$0.23 / $0.96	70	99.3%
2	Together#	2.57%	18k	$0.30 / $1.20	129	99.9%
3	ModelRun [by Modular]fp8#	4.26%	25k	$0.30 / $1.30	74	99.4%

Recommended OpenRouter settings for MiniMax M3

{
  "provider": {
    "order": [
      "coreweave/fp4",
      "together"
    ],
    "ignore": [
      "modelrun/fp8"
    ]
  }
}

Give llms.txt to your agent

Using MiniMax M3?

Get updates when its successor drops

And which provider to use.

For model makers

Broken structured outputs carry your model's name

Your users don't see the provider. They see your model failing.

Worst provider4.26%

of MiniMax M3's structured outputs fail on ModelRun [by Modular] (fp8).

Best to worst7×

as often on ModelRun [by Modular] (fp8) as on CoreWeave (fp4), its best provider.

Every day2k

broken structured outputs a day across its 3 providers.

Releasing a model? Make your own API the one every provider is measured against.

Set the bar for your model↵