Qwen (Alibaba)

Creator of the Qwen-VL vision-language model family. Qwen3-VL 8B offers strong multilingual OCR with a 262K context window.

Models on OpenOCR

Available now

~7,910 pages / $1~$0.000126 per standard page

Lowest reference cost

Available Models

Qwen: Qwen3.7 FlashLLM Vision

Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition and spatial understanding.

~7,910 pages / $1~$0.000126 per standard page

15187ms

Qwen: Qwen3 VL 235B A22B InstructLLM Vision

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use, including VQA, document parsing, chart and table extraction, and multilingual OCR. The series emphasizes robust perception, including recognition of diverse real-world and synthetic categories, spatial understanding through 2D/3D grounding, and long-form visual comprehension.

~678 pages / $1~$0.00148 per standard page

4407ms

Qwen: Qwen3.8 Omni FlashLLM Vision

Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba and the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization.

~2,050 pages / $1~$0.000487 per standard page

Qwen3-VL 235B A22B Instruct (DeepInfra)LLM Vision

Qwen/Qwen3-VL-235B-A22B-Instruct — OCR-capable vision model.

~1,000 pages / $1~$0.000996 per standard page

14067ms

Qwen2.5-VL 32B Instruct (DeepInfra)LLM Vision

Qwen/Qwen2.5-VL-32B-Instruct — OCR-capable vision model.

~467 pages / $1$0.00214/page

5184ms

Qwen: Qwen3 VL 30B A3B InstructLLM Vision

Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception of real-world and synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image, multi-turn instructions, video timeline alignments, and GUI automation.

~1,940 pages / $1~$0.000517 per standard page

4146ms

Qwen: Qwen3.6 35B A3BLLM Vision

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture.

~1,170 pages / $1~$0.000852 per standard page

6420ms

Qwen3-VL 30B A3B Instruct (DeepInfra)LLM Vision

Qwen/Qwen3-VL-30B-A3B-Instruct — OCR-capable vision model.

~2,470 pages / $1~$0.000404 per standard page

4499ms

Qwen: Qwen3.6 FlashLLM Vision

Qwen3.6 Flash is a fast, efficient language model from Alibaba’s Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Its pricing is tiered.

~1,270 pages / $1~$0.000789 per standard page

15374ms

Qwen: Qwen3.6 27BLLM Vision

Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities, accepting text, image, and video inputs.

~365 pages / $1~$0.00274 per standard page

10405ms

Qwen: Qwen3.7 PlusLLM Vision

Qwen3.7-Plus is a cost-effective model in Alibaba’s Qwen3.7 series. It supports text and image input with text output and builds on the series’ text capabilities.

~731 pages / $1~$0.00137 per standard page

16900ms

Qwen: Qwen3.5 Plus 2026-04-20LLM Vision

Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window.

~415 pages / $1~$0.00241 per standard page

13995ms

Qwen: Qwen3.8 27BLLM Vision

Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks. It features flexible thinking.

~455 pages / $1~$0.0022 per standard page

5151ms

Qwen: Qwen3.8 Max (0902)LLM Vision

Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba’s Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text.

~178 pages / $1~$0.00562 per standard page

Qwen: Qwen3.8 FlashLLM Vision

Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.

~2,200 pages / $1~$0.000454 per standard page

Qwen: Qwen3.8 Max PrimeLLM Vision

Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba’s Qwen team, served as a separate SKU at a higher price point. Its accepted modalities are text, image, and video.

~89 pages / $1~$0.0112 per standard page

Qwen: Qwen3.8 MaxLLM Vision

Qwen3.8 Max is the flagship model in Alibaba’s Qwen3.8 series and the general-availability successor to Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning and visual understanding.

~157 pages / $1~$0.00636 per standard page

14915ms

Coming Soon

Qwen3-VL-Reranker-8B

Coming Soon

Qwen: Qwen2.5 VL 32B Instruct

Qwen2.5-VL-32B is a multimodal vision-language model fine-tuned through reinforcement learning for enhanced mathematical reasoning, structured outputs, and visual problem-solving capabilities. It excels at visual analysis tasks, including object recognition, textual interpretation within images, and precise event localization in extended videos. Qwen2.5-VL-32B demonstrates state-of-the-art performance across multimodal benchmarks such as MMMU, MathVista, and VideoMME, while maintaining strong re

Coming Soon

Qwen3-VL 8B (Together)

Qwen3 Vision-Language 8B via Together AI — fast, accurate OCR with strong multilingual support.

Coming Soon