Qwen-VL OCR
Qwen-VL OCR is a language model from Qwen released on Oct 28, 2024. It reads text and images and writes text, with a 34K token context window and up to 4K tokens per reply.
Show moreShow less
It costs $0.07 per million input tokens and $0.16 per million output tokens.
2 providers serve it, including Alibaba (China). The lowest input price is $0.043 per million tokens at Alibaba (China).
- Modalities
- In / out price
- $0.07 / $0.16 per 1M
- Context
- 34K
- Max output
- 4K
- Released
- Oct 28, 2024
- Knowledge cutoff
- Apr 2024
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Qwen-VL OCR pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.07 / 1M tokens | |
|---|---|---|
| Output | $0.16 / 1M tokens |
Qwen-VL OCR providers
2 providers serve it, including Alibaba (China). The lowest input price is $0.043 per million tokens at Alibaba (China). Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| Alibaba First party | $0.07 | $0.16 | – | 34K | 4K |
| Alibaba (China) | $0.043 | $0.072 | – | 34K | 4K |
What Qwen-VL OCR costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call Qwen-VL OCR through an OpenAI compatible API.
- Temperature
temperature
Alternatives to Qwen-VL OCR
Models that take the same inputs, closest in price, cheaper ones first.
- 990K context
Reads text, images, audio and video. Tool calling. Served by 3 providers.
by googleFeb 5, 2025$0.052/M input tokens$0.21/M output tokens3 providers
- 262K context
Reads text, images and video. Tool calling, structured output, reasoning. Served by 5 providers.
by inclusionaiSep 8, 2026$0.06/M input tokens$0.18/M output tokens5 providers
- 128K context
Reads text and images. Reasoning. Served by 6 providers.
by nvidiaJun 4, 2026$0.05/M input tokens$0.15/M output tokens6 providers
- 131K context
Reads text and images. Tool calling, structured output. Served by 9 providers.
by googleDec 1, 2024$0.05/M input tokens$0.15/M output tokens9 providers
- 128K context
Reads text, images and video. Tool calling, structured output, reasoning. Served by 6 providers.
by z-aiDec 8, 2025$0.0218/M input tokens$0.2184/M output tokens6 providers
- 262K context
Reads text and images. Tool calling, structured output.
by qwenOct 15, 2025$0.022/M input tokens$0.215/M output tokens
More from Qwen
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
Qwen-VL OCR questions
How much does the Qwen-VL OCR API cost?
$0.07 per million input tokens and $0.16 per million output tokens. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Qwen-VL OCR?
34,096 tokens of input, and it can write up to 4,096 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Qwen-VL OCR?
2 providers serve it, including Alibaba (China). The lowest input price is $0.043 per million tokens at Alibaba (China). Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Qwen-VL OCR support tool calling?
Not through the standard tools parameter. For an agent that calls your APIs, pick a model from the alternatives below that does.
Is Qwen-VL OCR open source?
No. Qwen serves it through an API only, so you cannot download the weights or host it yourself.
When was Qwen-VL OCR released?
Oct 28, 2024, with training data up to Apr 2024.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.
Building on Qwen-VL OCR?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting