Model Catalog › qwen

Qwen-VL OCR

qwen-vl-ocr

CHAT Light tier Multimodal Proprietary (API-only)

Qwen-VL OCR (qwen-vl-ocr) is a chat model from qwen with a 34.1K-token context window; proprietary (API-only); capabilities vision; input image, text; output text.

34.1KContext
4.1KMax output
$0.07$ / 1M in

Pricing

Input
$0.07 / 1M tokens
Output
$0.16 / 1M tokens
Currency
USD
Note
Indicative US list price — verify with the vendor.

Indicative US list price — a reference only, verify with the vendor. Source: models-dev. Last verified 2026-10-30.

Specifications

Context window
34,096 tokens (34.1K)
Max output
4,096 tokens
Weights
Proprietary (API-only)
Input modalities
image text
Output modalities
text
Knowledge cutoff
2024-04
Release date
2024-10-28

Capabilities

vision

Provenance

models-dev
Last verified: 2026-10-30

Related models

Qwen-Turbo
qwen-turbo
qwen · CHAT · 129.0K ctx
GLM-5.2
glm-5.2
qwen · CHAT · 1.0M ctx
Kimi K3
kimi-k3
qwen · CHAT · 1.0M ctx
DeepSeek V4 Flash 0731
deepseek-v4-flash-0731
qwen · CHAT · 1M ctx
Qwen-Coder
qwen-coder
qwen · CHAT · 1M ctx
Qwen3.5 Flash
qwen3.5-flash
qwen · CHAT · 1M ctx