How Much Does Document Extraction Cost per Month?
At production volume (500,000 calls/month), the cheapest effective option is Amazon Nova Micro at $118/month. The most expensive frontier option, GPT-5.4 Pro, runs $113,400/month — Extraction reads a medium-sized document and returns a small, fixed-schema JSON object — the output is small and predictable by design.
How much does document extraction cost per month?
At production volume (500,000 calls/month), the cheapest effective option for document extraction is Amazon Nova Micro at $118 per month, verbosity-adjusted rather than list price. The most expensive frontier model, GPT-5.4 Pro, runs $113,400 per month for the same workload.
Token shape
| Shape | medium document in, tiny structured JSON out |
| Input / output tokens per call | 6K in / 0K out |
| Cacheable input | 15% |
| Batch-eligible | Yes |
Input is one document per call (schema and instructions are the only stable, cacheable part); output is a compact JSON object matching a fixed schema. This runs at real volume, so batch discounts matter.
Volume
Ranked cost — Production volume (caching + batch applied where available)
| Model | Provider | List monthly | Effective monthly | Verbosity | Rank Δ |
|---|---|---|---|---|---|
| Amazon Nova Microbudget | Amazon | $123 | $104 | 0.76× | — |
| Llama 3.1 8Bbudgetlegacy | Groq | $160 | $78.85 | 0.77× | — |
| GPT-5 Nanobudgetlegacy | OpenAI | $200 | $180 | — | — |
| Amazon Nova Litebudget | Amazon | $210 | $183 | 0.92× | — |
| GPT-OSS 20Bbudget | Groq | $263 | $167 | 2.93× | — |
| Gemini 2.5 Flash Litebudgetlegacy | $350 | $310 | — | — | |
| Ministral 8Bbudget | Mistral | $469 | $234 | 0.93× | ▲1 |
| DeepSeek V4 Flashbudget | DeepSeek | $455 | $454 | 2.60× | ▼1 |
| Mistral Small 3.1budget | Mistral | $525 | $257 | 0.85× | ▲3 |
| GPT-4o Minibudgetlegacy | OpenAI | $525 | $464 | — | ▼1 |
| Grok-3 Minibudgetlegacy | xAI | $525 | $525 | — | ▼1 |
| GPT-OSS 120Bbudget | Groq | $525 | $294 | 1.83× | ▼1 |
| Llama 4 Maverickbudgetlegacy | Groq | $675 | $337 | — | — |
| GPT-5.4 Nanobudgetlegacy | OpenAI | $756 | $642 | 0.79× | ▲1 |
| GPT-5.6 Lunabudget | OpenAI | $750 | $669 | — | ▼1 |
Show all 63 models
| Gemini 3.1 Flash Litebudgetlegacy | $938 | $814 | 0.88× | ▲1 | |
| Gemini 3.5 Flash Litebudget | $938 | $836 | — | ▼1 | |
| Codestralbudget | Mistral | $1,013 | $494 | 0.79× | ▲1 |
| GPT-5 Minibudgetlegacy | OpenAI | $1,000 | $899 | — | ▼1 |
| Gemini 2.5 Flashbudgetlegacy | $1,213 | $1,091 | — | ▲1 | |
| GPT-OSS 120B (Cerebras)budget | Cerebras | $1,144 | $1,268 | 2.33× | ▼1 |
| Mistral Medium 3budget | Mistral | $1,450 | $705 | 0.84× | ▲1 |
| DeepSeek V4 Probudget | DeepSeek | $1,414 | $1,489 | 3.31× | ▼1 |
| Llama 3.3 70Bbudgetlegacy | Groq | $1,869 | $925 | 0.81× | — |
| GLM-5.1midlegacy | Z.ai | $2,075 | $2,075 | — | — |
| Qwen 3.8 30Bmid | Groq | $2,175 | $1,088 | — | — |
| Qwen 3.6 27Bmidlegacy | Groq | $2,175 | $1,088 | — | — |
| Qwen 3.7 Plusmid | Qwen | $2,650 | $2,650 | — | — |
| Amazon Nova Promid | Amazon | $2,800 | $2,476 | — | — |
| GPT-5.4 Minimidlegacy | OpenAI | $2,813 | $2,509 | — | — |
| Gemini 3.1 Flashmidlegacy | $2,813 | $2,509 | — | — | |
| Claude Haiku 4.5mid | Anthropic | $3,625 | $3,220 | — | — |
| o3-Minimidlegacy | OpenAI | $3,850 | $3,405 | — | — |
| Grok 4.3mid | xAI | $4,063 | $4,194 | 1.42× | — |
| GPT-5midlegacy | OpenAI | $5,000 | $4,494 | — | ▲1 |
| Qwen 3.8 Maxmid | Qwen | $5,600 | $5,600 | — | ▲1 |
| Qwen 3.7 Maxmid | Qwen | $5,600 | $5,600 | — | ▲1 |
| Gemini 3.6 Flashmid | $5,625 | $5,017 | — | ▲1 | |
| Gemini 3.5 Flashmidlegacy | $5,625 | $5,017 | — | ▲1 | |
| GLM-5.2mid | Z.ai | $4,750 | $6,329 | 3.87× | ▼5 |
| Grok-3midlegacy | xAI | $6,500 | $6,500 | — | — |
| Grok-4.20 Reasoningmid | xAI | $6,750 | $6,750 | — | — |
| Grok-4.20mid | xAI | $6,750 | $6,750 | — | — |
| Mistral Large 3mid | Mistral | $6,750 | $3,375 | — | — |
| Gemini 3.1 Promid | $7,500 | $6,135 | 0.63× | ▲3 | |
| GPT-4.1midlegacy | OpenAI | $7,000 | $6,190 | — | ▼1 |
| GPT-5.6 Terramid | OpenAI | $7,500 | $6,690 | — | — |
| GPT-4omidlegacy | OpenAI | $8,750 | $7,738 | — | ▲1 |
| GLM 4.7 (Cerebras)mid | Cerebras | $7,094 | $9,345 | 7.55× | ▼3 |
| GPT-5.4midlegacy | OpenAI | $9,375 | $8,362 | — | — |
| Claude Sonnet 4.6mid | Anthropic | $10,875 | $9,660 | — | — |
| Claude Sonnet 4.5midlegacy | Anthropic | $10,875 | $9,660 | — | — |
| Claude Sonnet 4midlegacy | Anthropic | $10,875 | $9,660 | — | — |
| Claude Opus 4.8mid | Anthropic | $18,125 | $15,975 | 0.96× | — |
| Claude Opus 4.7midlegacy | Anthropic | $18,125 | $16,100 | — | — |
| Claude Opus 4.6midlegacy | Anthropic | $18,125 | $16,100 | — | — |
| Claude Opus 4.5midlegacy | Anthropic | $18,125 | $16,100 | — | — |
| GPT-5.6 Solfrontier | OpenAI | $18,750 | $16,725 | — | — |
| GPT-4 Turbofrontierlegacy | OpenAI | $33,750 | $29,700 | — | — |
| Claude Fable 5frontier | Anthropic | $36,250 | $32,200 | — | — |
| Claude Opus 4.1frontierlegacy | Anthropic | $54,375 | $48,300 | — | — |
| Claude Opus 4frontierlegacy | Anthropic | $54,375 | $48,300 | — | — |
| GPT-5.4 Profrontierlegacy | OpenAI | $112,500 | $101,250 | 1.04× | — |
Prompt caching assumes a 90% saving on the cacheable share of input — a stated modelling assumption, providers publish 75-90% off. See the full formula and coverage disclosure →