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 — Qwen3.5-35B-A3B
- Cost
- $0.313 in · $1.25 out per 1M tokensBudget
- Memory
- 262K tokens — about 400 pages
- Reads
- Text · Images · Video
- Can do
- Use tools (agents)
- Structured output
- Thinking mode
- Good at
- Coding: better than 35%
- Reliability
- 99.97% uptime, last 24h
- Released
- Feb 25, 2026
Advanced details
- API model ID
qwen/qwen3.5-35b-a3b- Max output
- 16K tokens
- Max input
- 258K tokens
- Cached input
- $0.156 per 1M
- Tokenizer
- Qwen3
- Coding index
- 37.0
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 |
|---|---|---|---|---|---|
| Darkbloom · fp4 | $0.08 | $0.75 | — | 33K | 99.69% |
| DeepInfra · fp8 | $0.14 | $1.00 | $0.05 | 82K | 99.97% |
| Parasail · fp8 | $0.15 | $1.00 | $0.05 | 236K | 99.96% |
| Alibaba | $0.163 | $1.30 | — | 66K | 85.91% |
| AtlasCloud · fp8 | $0.225 | $1.80 | $0.225 | 66K | 98.75% |
| SiliconFlow · fp8 | $0.24 | $1.80 | $0.15 | 236K | 97.98% |
| Venice | $0.313 | $1.25 | $0.156 | 16K | 99.93% |
Supported parameters
- frequency_penalty
- include_reasoning
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- reasoning
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- top_p
Live from OpenRouter, refreshed hourly. Scores from Artificial Analysis.
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