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 — Qwen3 VL 235B A22B Instruct
- Cost
- $0.21 in · $1.90 out per 1M tokensBudget
- Memory
- 262K tokens — about 400 pages
- Reads
- Text · Images
- Can do
- Use tools (agents)
- Structured output
- Thinking mode (not supported)
- Reliability
- 99.22% uptime, last 24h
- Released
- Sep 23, 2025
Advanced details
- API model ID
qwen/qwen3-vl-235b-a22b-instruct- Max output
- 33K tokens
- Max input
- 129K tokens
- Cached input
- $0.10 per 1M
- Knowledge cutoff
- 2025-03-31
- Tokenizer
- Qwen3
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 |
|---|---|---|---|---|---|
| DeepInfra · fp8 | $0.20 | $0.88 | $0.11 | 16K | 97.66% |
| Venice · fp8 | $0.21 | $1.90 | $0.10 | 16K | 97.89% |
| Parasail · fp8 | $0.21 | $1.90 | $0.10 | 33K | 99.05% |
| Alibaba | $0.26 | $1.04 | — | 33K | 99.22% |
| Novita · bf16 | $0.30 | $1.50 | — | 33K | 95.05% |
Supported parameters
- frequency_penalty
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- 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