Alibaba (Qwen) · Released Sep 2024Qwen2.5-VL 72B Instruct
Qwen vision-language model for visual reasoning, documents, and agent tasks.
- Capability
- —No ECI score yet
- Input
- $2.80per 1M tokens
- Output
- $8.40per 1M tokens
- Context
- 131K8K max output
What it costs
- Input
- $2.80per million tokens
- Output
- $8.40per million tokens
- Blended (3:1)
- $4.20pricier than 84% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $9.80 |
| Team assistant25M input + 5M output tokens | $112.00 |
| Production app250M input + 50M output tokens | $1,120 |
Official Alibaba API price, as listed on models.dev.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for Qwen2.5-VL 72B Instruct yet.
The details
- Lab
- Alibaba (Qwen)
- Released
- Sep 2024
- Knowledge cutoff
- Apr 2024
- Context window
- 131,072 tokens
- Max output
- 8,192 tokens
- Inputs
- Text, Images
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- No
- Weights
- Open weights
- API model ID
qwen2-5-vl-72b-instructon Alibaba- Availability
- 1 API providerlisted on models.dev
More from Alibaba (Qwen)
About Qwen2.5-VL 72B Instruct
How much does Qwen2.5-VL 72B Instruct cost?
Qwen2.5-VL 72B Instruct costs $2.80 input / $8.40 output per million tokens (official Alibaba API price). At a 3:1 input-to-output mix that is $4.20 per million tokens, more expensive than 84% of the 360 priced models we track.
What is the context window of Qwen2.5-VL 72B Instruct?
Qwen2.5-VL 72B Instruct accepts up to 131,072 tokens per request and can write up to 8,192 tokens in one response.
How good is Qwen2.5-VL 72B Instruct?
Epoch AI has not published a Capabilities Index score for Qwen2.5-VL 72B Instruct yet.
Is Qwen2.5-VL 72B Instruct open source?
Yes. Alibaba (Qwen) publishes the weights, so it can be downloaded and self-hosted.
What inputs does Qwen2.5-VL 72B Instruct support?
Qwen2.5-VL 72B Instruct accepts text and images and replies in text. It is not a dedicated reasoning model, supports tool calling.
When was Qwen2.5-VL 72B Instruct released?
Alibaba (Qwen) released Qwen2.5-VL 72B Instruct on Sep 2024. Its training data runs to Apr 2024.
What are the best alternatives to Qwen2.5-VL 72B Instruct?
The closest current models from other labs on capability, price and release date are Command R+ (Cohere, $2.50 / $10.00), Palmyra X4 (Writer, $2.50 / $10.00), Step 1 (32K) (StepFun, $2.05 / $9.59) and Sonar Deep Research (Perplexity, $2.00 / $8.00).