ذكاء نماذج الذكاء الاصطناعي

PaddleOCR-VL

novita-ai/paddleocr-vl

من novita-ai · أُصدِر 2025-10-22

$0.020
الإدخال / 1M رمز
$0.020
الإخراج / 1M رمز
16K
نافذة السياق
16K
أقصى إخراج

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

القدرات

استدعاء الأدواتتفكير? إخراج منظمالمرفقاتأوزان مفتوحةالتحكم بالحرارة
الوسائط المدعومة: إدخال text, image · إخراج text

Model fit scores

0–100 · higher is better

These scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.

Coding1
  • Tool calling0/40
  • Structured output0/20
  • Reasoning0/10
  • Context window (100K → 1M)0/20
  • Provider availability1/10
Agents11
  • Tool calling0/35
  • Structured output0/25
  • Reasoning0/15
  • Output token limit10/15
  • Provider availability1/10
JSON / structured output30
  • Structured output / JSON mode0/50
  • Tool calling0/20
  • Temperature control10/10
  • Price-friendly for high-volume20/20
Cost efficiency95
  • Headline price (log-scaled)95/95
  • Has prompt-cache pricing0/5
Long context0
  • Context ≥ 100K0/100
Vision64
  • Accepts image input50/50
  • Context window (10K → 1M)3/30
  • Has published price10/10
  • Provider availability1/10
Production-readiness58
  • Number of independent providers5/40
  • Has published per-token price20/20
  • Context window ≥ 8K8/15
  • No data inconsistencies across providers10/10
  • Official model (not derivative)15/15

Cost Efficiency Index

Open full calculator →

Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.

ScenarioCostAssumption
RAG answer
per 1,000 RAG answers
$0.11
< $0.01 per request
5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot.
Support ticket triage
per 10,000 tickets
$0.22
< $0.01 per request
1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support.
Data extraction
per 1,000 documents
$0.05
< $0.01 per request
2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines.
Code review
per 1,000 PRs
$0.18
< $0.01 per request
8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads.
Agent step
per 1,000 steps
$0.25
< $0.01 per request
12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step.

تفاصيل التسعير

السعر المُوصى به من novita-ai · paddlepaddle/paddleocr-vl

$0.020
إدخال
$0.020
إخراج

متاح لدى 1 مزود

المزودمعرف نموذج المزودإدخال / 1Mإخراج / 1Mالسياقتاريخ الإصدار
NovitaAI
novita-ai
paddlepaddle/paddleocr-vl$0.020$0.02016K2025-10-22

Frequently asked questions

How much does PaddleOCR-VL cost?

PaddleOCR-VL costs $0.020 per 1M input tokens and $0.020 per 1M output tokens, sourced from novita-ai. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.

What is the context window of PaddleOCR-VL?

PaddleOCR-VL has a context window of 16K tokens, with a max output of 16K tokens per reply. This is the total combined size of prompt + completion.

Does PaddleOCR-VL support tool calling?

No. PaddleOCR-VL does not support tool calling (function calling). If your workflow requires it, look at the /capabilities/tool-calling list for alternatives.

Does PaddleOCR-VL support structured output / JSON mode?

Support for structured output / JSON-schema-constrained decoding is not reported for PaddleOCR-VL in our data source. Verify with novita-ai's official documentation before relying on it in production.

Can PaddleOCR-VL accept image input?

Yes. PaddleOCR-VL accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check novita-ai's docs for the exact rule.

Is PaddleOCR-VL open-weight?

Yes. PaddleOCR-VL's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.

What are the best alternatives to PaddleOCR-VL?

If PaddleOCR-VL doesn't fit, consider Ling-2.6-1T, Ling-2.6-flash, baichuan-m2-32b. Each one targets the same use case — see the Related links below for direct head-to-head pages.

Where does this data come from?

All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.

More novita-ai models

Capability lists this model is in

آخر تحديث:

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.