$0.040 in / $0.160 out
- Context: 131K
- Providers: 33
- Tool calling
- Structured output
- Reasoning
- Open weights
Best AI models · 2026-05-12
Best AI Models for JSON Output and Structured Data
Models with explicit structured output / JSON mode + tool calling support.
How we picked these
- We give 50 points for explicit structured output / JSON mode support.
- Tool calling adds 20 points (often paired with JSON in real systems).
- Cheap models get a small bonus — JSON workloads tend to be high-volume.
Top 10 picks
$0.950 in / $4.00 out
- Context: 262K
- Providers: 31
- Tool calling
- Structured output
- Reasoning
- Vision
- Open weights
$0.030 in / $0.140 out
- Context: 131K
- Providers: 23
- Tool calling
- Structured output
- Reasoning
- Open weights
$0.600 in / $3.60 out
- Context: 262K
- Providers: 22
- Tool calling
- Structured output
- Reasoning
- Vision
- Open weights
$0.300 in / $2.50 out
- Context: 1.05M
- Providers: 21
- Tool calling
- Structured output
- Reasoning
- Vision
$0.500 in / $3.00 out
- Context: 1.05M
- Providers: 18
- Tool calling
- Structured output
- Reasoning
- Vision
$0.400 in / $1.60 out
- Context: 1.05M
- Providers: 16
- Tool calling
- Structured output
- Vision
$0.150 in / $0.600 out
- Context: 128K
- Providers: 15
- Tool calling
- Structured output
- Vision
$0.140 in / $0.280 out
- Context: 1M
- Providers: 15
- Tool calling
- Structured output
- Reasoning
- Open weights
$0.027 in / $0.109 out
- Context: 131K
- Providers: 14
- Tool calling
- Structured output
- Vision
- Open weights
Recommended stack by tier
Same shortlist sliced four ways — pick the tier that matches your budget and constraints.
Budget
Google$0.027 in / $0.109 out · 131K ctx
Lowest total per-1M-token cost in this list ($0.14).
Lowest-cost option that still meets the use case. Pick this when you have high volume or strict unit-economics.
Balanced
OpenAI$0.400 in / $1.60 out · 1.05M ctx
Median price ($2.00) — typically the safest default.
Good-enough quality at a mid-tier price. The default choice for most production apps.
Premium
Moonshot AI$0.950 in / $4.00 out · 262K ctx
Highest-priced pick in the list ($4.95) — usually the flagship.
Highest-capability model in this list. Pick when accuracy or reasoning matters more than cost.
Open-weight
No fit in this list
Open weights — self-host on your own GPUs, fine-tune on private data, run offline. Pricing here reflects the cheapest API host.
Frequently asked questions
Which AI model is the best for structured / JSON output in 2026?
Right now we put GPT OSS 120B from OpenAI at the top, primarily because it explicitly supports JSON-schema-constrained decoding, not just 'reply in JSON'. Rankings are recomputed from live model metadata — see "How we picked these" above for the exact rule.
What is the cheapest option in this list?
Gemma 3 27B (Google) is the lowest-priced pick at $0.027 per 1M input tokens and $0.109 per 1M output tokens. Costs from other entries scale up from there.
How are these rankings generated?
Each pick comes from a programmatic rule defined in our use-case-rules config: a hard filter (e.g. tool calling required, context ≥ 100K) plus a numeric score combining capability, context window and price. We never hand-curate the order, but we do hand-curate the rule. The full data source is the models.dev API, refreshed daily.
How often is this page updated?
The underlying model data is refreshed once per day from models.dev, and the static page is rebuilt when the data changes. The 'Last updated' date below shows the most recent rebuild.
Explore more
Top picks · model details
- GPT OSS 120B$0.04 in / $0.16 out
- Kimi K2.6$0.95 in / $4.00 out
- GPT OSS 20B$0.03 in / $0.14 out
- Qwen3.5 397B-A17B$0.60 in / $3.60 out
- Gemini 2.5 Flash$0.30 in / $2.50 out
Other best-of lists
Browse by capability
Vendors in this list
Last updated:
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.