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 providers

6 models · 1.9M structured outputs a day

#	Model	Broken structured outputs	Rank	Best for this model	Structured outputs a day
1	Gemma 4 26B A4Bbf16	0.23%	1 of 11	—	334k
2	Qwen3.5-9Bbf16	0.30%	1 of 6	—	107k
3	GLM 5.3 Flash	0.95%	12 of 29	Parasail (fp4) 0.28%	1.3M
4	DeepSeek V4.1 Flash 1017	0.99%	11 of 33	Reka AI 0.40%	41k
5	DeepSeek V4.1 Flash	2.68%	23 of 28	DeepInfra (fp8/flex) 0.35%	90k
6	GLM 5.3	10.28%	25 of 28	Together 0.25%	9.0k

New models

Get updates when a new model drops

And which provider to use.

For inference providers

Structured outputs don't have to break

The same provider can handle structured outputs well on one model and struggle on the next. Implementations diverge on strings, optionals, composition and conditionals (the April announcement): the schema one provider enforces, another ignores.

Worst model10.28%

of GLM 5.3's structured outputs fail on Prime Intellect.

Best model0.23%

on Gemma 4 26B A4B, its best model.

Ignored on1 of 6

models, where the settings tell OpenRouter to skip Prime Intellect.

dotjson plugs into your inference stack, so every model you serve gets perfect structured outputs from day 0.

Fix Prime Intellect's structured outputs↵