Qwen
Alibaba's open-weight family, with a coder model in nearly every size.
Qwen is Alibaba's model family and the largest open-weight line there is — dozens of sizes from a few billion parameters up to the Max models, most of them published so you can run them yourself. For vibe coders the draw is the Qwen Coder models: strong at code for the price, cheap to call through a provider, and small enough at the low end to run on your own machine. The flagship Max models take text, images and video and go up to a million tokens of context.
At a glance — Qwen2.5 VL 72B Instruct
- Cost
- $0.80 in · $1.00 out per 1M tokensMid-range
- Memory
- 128K tokens — about 200 pages
- Reads
- Text · Images
- Can do
- Use tools (agents) (not supported)
- Structured output
- Thinking mode (not supported)
- Reliability
- 100.00% uptime, last 24h
- Released
- Feb 1, 2025
Advanced details
- API model ID
qwen/qwen2.5-vl-72b-instruct- Max output
- 115K tokens
- Cached input
- $0.40 per 1M
- Knowledge cutoff
- 2024-06-30
- Tokenizer
- Qwen
Providers
The same model, hosted by different companies. OpenRouter picks one per request and falls back to the next if it fails.
| Provider | Input /1M | Output /1M | Cached /1M | Max output | Uptime 24h |
|---|---|---|---|---|---|
| Parasail · fp8 | $0.80 | $1.00 | $0.40 | 115K | 100.00% |
Supported parameters
- frequency_penalty
- logit_bias
- logprobs
- max_tokens
- presence_penalty
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- top_k
- top_logprobs
- top_p
Live from OpenRouter, refreshed hourly.
Key info
- Pricing
- Open source
- Category
- Models
- Best for
- Intermediate
- Made by
- Alibaba
- Weights
- Open, most sizes
- Good for
- Cheap coding models, and running one yourself