20 Cheapest Models With Structured Output
Models with native JSON or schema output, ranked by blended price. · verified 2026-10-11
#1 is Llama 3.2 1B Instruct at $0.02 input and $0.02 output per million tokens.
// ranking
| # | model | lab | in $/1M | out $/1M | ctx |
|---|---|---|---|---|---|
| 1 | Llama 3.2 1B Instruct | Meta | $0.02 | $0.02 | 131K |
| 2 | Llama-3.1-8B-Instruct | Meta | $0.02 | $0.05 | 16.4K |
| 3 | Voxtral Mini 3B 2507 | Mistral | $0.04 | $0.04 | 32.8K |
| 4 | Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | |
| 5 | Qwen3.7 Flash | Alibaba (Qwen) | $0.03 | $0.13 | 1M |
| 6 | DeepSeek V4 Flash 0731 | DeepSeek | $0.06 | $0.18 | 1.05M |
| 7 | Gemma 3 27B IT | $0.08 | $0.16 | 131.1K | |
| 8 | Ministral 3 3B | Mistral | $0.10 | $0.10 | 131.1K |
| 9 | GPT OSS 120B | OpenAI | $0.05 | $0.25 | 131.1K |
| 10 | GPT OSS Safeguard 20B | OpenAI | $0.07 | $0.20 | 128K |
| 11 | Qwen3.5 9B | Alibaba (Qwen) | $0.10 | $0.15 | 262.1K |
| 12 | DeepSeek V4 Flash | DeepSeek | $0.09 | $0.18 | 1.05M |
| 13 | gpt-oss-20b | OpenAI | $0.07 | $0.30 | 131.1K |
| 14 | Gemma 4 26B A4B IT | $0.07 | $0.34 | 262.1K | |
| 15 | GPT-5 Nano | OpenAI | $0.05 | $0.40 | 400K |
| 16 | GLM-4.7-Flash | Z.AI (Zhipu) | $0.0605 | $0.40 | 131.1K |
| 17 | Ministral 3 8B | Mistral | $0.15 | $0.15 | 262.1K |
| 18 | Mistral Small 3.1 24B | Mistral | $0.10 | $0.30 | 128K |
| 19 | Voxtral Small 24B 2507 | Mistral | $0.10 | $0.30 | 32.8K |
| 20 | Qwen3.5 Flash | Alibaba (Qwen) | $0.10 | $0.40 | 1M |