AI 모델 인텔리전스

기능 · 2026-05-12

AI Models with Structured Output Support

AI models that support JSON mode / structured output for reliable data extraction.

이게 뭔가요?

  • Structured output (sometimes called JSON mode or response_format=json_schema) constrains the model to emit a JSON document that matches a schema you provide.
  • Unlike a plain prompt that says "reply in JSON", structured output is enforced at decode time — the model literally cannot emit invalid JSON.

왜 중요한가

  • It eliminates JSON parsing errors and jailbreak prefixes like "Sure! Here's the JSON: ...".
  • It is essential for any pipeline that pipes LLM output into a typed system: data extraction, classification, structured summarisation.

이 기능을 지원하는 모델 206개

모델벤더입력 / 1M출력 / 1M컨텍스트제공자
Voxtral Small 24B 2507Mistral$0.002$0.00232K3
dots.ocrchutes$0.010$0.011131K1
Hermes 4 14Bchutes$0.014$0.05441K1
Sao10k L3 8B Lunaris novita-ai$0.050$0.0508K1
Gemma 3 12BGoogle$0.030$0.10033K10
Gemma 3 27BGoogle$0.027$0.109131K14
DeepSeek R1 Distill Llama 70BDeepSeek$0.027$0.1098K5
GPT OSS 20BOpenAI$0.030$0.140131K23
GPT OSS 120BOpenAI$0.040$0.160131K33
Qwen/Qwen3-VL-30B-A3B-ThinkingAlibaba (Qwen)$0.100$0.100262K6
Qwen/Qwen3-VL-30B-A3B-InstructAlibaba (Qwen)$0.100$0.100262K6
Qwen/Qwen3-VL-8B-InstructAlibaba (Qwen)$0.100$0.100262K5
deepseek-ai/DeepSeek-R1-Distill-Qwen-14BDeepSeek$0.100$0.100131K4
Ministral 3Bllmgateway$0.100$0.100131K1
Mistral Small 3.2 24B InstructMistral$0.060$0.18096K3
GPT OSS 20Bdatabricks$0.050$0.200131K1
GPT OSS Safeguard 20BOpenAI$0.070$0.200128K6
Qwen/Qwen2.5-VL-32B-InstructAlibaba (Qwen)$0.050$0.220131K6
GPT OSS 20Bfrogbot$0.070$0.200131K1
Hermes 2 Pro Llama 3 8BMeta$0.140$0.1408K4
Qwen 2.5 72B InstructAlibaba (Qwen)$0.062$0.23132K3
Ministral 8Bllmgateway$0.150$0.150262K1
Qwen3 Coder 30B A3B InstructAlibaba (Qwen)$0.070$0.270262K3
inclusionAI/Ling-mini-2.0siliconflow-cn$0.070$0.280131K1
inclusionAI/Ling-mini-2.0siliconflow$0.070$0.280131K1
GPT OSS 120Bdatabricks$0.072$0.280131K1
deepseek-ai/DeepSeek-R1-Distill-Qwen-32BDeepSeek$0.180$0.180131K6
Seed 1.6 Flash (250715)llmgateway$0.070$0.300256K1
Gemini 2.0 Flash LiteGoogle$0.075$0.3001.05M8
MiMo V2 Flash TEEchutes$0.090$0.290262K1
Gemma 4 26BGoogle$0.100$0.300256K8
Ling-2.6-flashnovita-ai$0.100$0.300262K1
XiaomiMiMo/MiMo-V2-Flashnovita-ai$0.100$0.300262K1
Ministral 14Bllmgateway$0.200$0.200262K1
Llama 3.2 11B InstructMeta$0.070$0.330128K1
DeepSeek V4 FlashDeepSeek$0.140$0.2801M15
Phi-4-mini-instructMicrosoft$0.080$0.350128K4
GPT-5 NanoOpenAI$0.050$0.400400K17
Gemini 2.5 Flash LiteGoogle$0.100$0.4001.05M13
GPT-4.1 nanoOpenAI$0.100$0.4001.05M12
Gemini 2.5 Flash Lite Preview 09-25Google$0.100$0.4001.05M9
Gemini 2.0 FlashGoogle$0.100$0.4001.05M6
Gemini 2.0 FlashGoogle$0.100$0.4001.05M3
Qwen/Qwen3-Omni-30B-A3B-ThinkingAlibaba (Qwen)$0.100$0.40066K3
Qwen/Qwen3-Omni-30B-A3B-InstructAlibaba (Qwen)$0.100$0.40066K3
Qwen3.5 FlashAlibaba (Qwen)$0.100$0.4001M3
Gemini Flash-Lite LatestGoogle$0.100$0.4001.05M2
Gemma 4 31BGoogle$0.130$0.380256K11
Qwen/Qwen3-VL-32B-InstructAlibaba (Qwen)$0.104$0.416262K3
Hermes 4 70Bopenrouter$0.130$0.400131K1
Hermes-4-70Bnebius$0.130$0.400128K1
GPT OSS 20Bllmgateway$0.100$0.500131K1
inclusionAI/Ling-flash-2.0siliconflow-cn$0.140$0.570131K1
inclusionAI/Ring-flash-2.0siliconflow-cn$0.140$0.570131K1
tencent/Hunyuan-A13B-Instructsiliconflow-cn$0.140$0.570131K1
inclusionAI/Ring-flash-2.0siliconflow$0.140$0.570131K1
inclusionAI/Ling-flash-2.0siliconflow$0.140$0.570131K1
tencent/Hunyuan-A13B-Instructsiliconflow$0.140$0.570131K1
GPT-4o miniOpenAI$0.150$0.600128K15
Gemini 2.5 Flash Preview 05-20Google$0.150$0.6001.05M4

전체 206개 중 상위 60개 표시. 추가 필터링은 전체 목록을 이용하세요.

Frequently asked questions

How many AI models support 구조화 출력?

206 canonical models in our database currently support 구조화 출력. The list is regenerated on every data refresh, so it always reflects the latest model releases from models.dev.

What is the cheapest model with 구조화 출력?

Voxtral Small 24B 2507 from Mistral is currently the lowest-priced option, at $0.002 per 1M input tokens and $0.002 per 1M output tokens. The full table above is sorted price-ascending.

Which model with 구조화 출력 has the largest context window?

GPT-5.4 (OpenAI) leads on context at 1.05M tokens. This may matter if you also need long-document understanding alongside 구조화 출력.

Which models are available on the most providers?

Production-readiness usually correlates with how many independent providers host the same weights. The top three by provider count are: Kimi K2.5 (45), GPT OSS 120B (33), GLM-5.1 (33).

How is 구조화 출력 different from a regular LLM?

Structured output (a.k.a. JSON mode / response_format=json_schema) constrains the model at decode time so it cannot emit invalid JSON. This is stricter than just prompting 'reply in JSON' and removes a whole class of parsing errors.

How often is this list updated?

Daily. Our data pipeline pulls models.dev once a day, regenerates the canonical model list, and rebuilds these pages so newly released models appear within 24 hours.

마지막 업데이트:

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.