Qwen-VL OCR
alibaba-cn/qwen-vl-ocr · family qwen · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: text image.
$0.05
Blended $/1M (3:1)
$0.043
Input $/1M
$0.072
Output $/1M
$0.11
1M in + 1M out
—
Cache read $/1M
#695 of 7,713
Cheapest rank
- Provider
- Alibaba (China) (
alibaba-cn) - Kind
- text (outputs text)
- Context
- 34,096 tokens
- Max output
- 4,096 tokens
- Capabilities
- text image
Same model, other providers
“Qwen-VL OCR” is offered by 2 providers — cheapest-effective first. This one (Alibaba (China)) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Alibaba (China) (this) | $0.043 | $0.072 | $0.05 | 34k |
| Alibaba | $0.72 | $0.72 | $0.72 | 34k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Alibaba (China) and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"qwen-vl-ocr","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):