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

Mistral · 3 providers · 825k structured outputs a day

#	Provider		Structured outputs a day	$ in / out per M	Tokens/s	Uptime
1	Parasailfp8#	0.15%	65k	$0.03 / $0.03	104	99.7%
2	DeepInfrafp8#	1.55%	246k	$0.03 / $0.03	33	100.0%
3	DekaLLMfp8#	2.24%	514k	$0.02 / $0.03	9	99.9%

Also ignored, under 1,000 structured outputs a day: Mistral 4.22%.

Recommended OpenRouter settings for Mistral Nemo

{
  "provider": {
    "order": [
      "parasail/fp8",
      "deepinfra/fp8",
      "dekallm/fp8"
    ],
    "ignore": [
      "mistral/eu"
    ]
  }
}

Give llms.txt to your agent

Using Mistral Nemo?

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 provider2.24%

of Mistral Nemo's structured outputs fail on DekaLLM (fp8).

Best to worst15×

as often on DekaLLM (fp8) as on Parasail (fp8), its best provider.

Every day15k

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↵