Skip to main content

​
Qwen (Alibaba Cloud)

Uses SSE streaming with OpenAI-compatible tool-calling format. Supports vision (base64 images) and reasoning content. Qwen offers one of the widest model ranges of any provider — from the ultra-cheap Qwen 3.5 Flash at 0.06/0.06/0.24 per MTok to the frontier Qwen 3.8 Max. All Qwen3+ models support three reasoning modes (None, High, Max) and up to 1M context. The dedicated Qwen3 Coder Plus model is tuned for code generation tasks. Since v1.0.235, connecting Qwen auto-selects Qwen 3.8 Max — the new flagship, and the first Max tier to add vision, at a lower price than the 3.7 Max it replaces. Best for: Cost-efficient agentic workflows, code generation, multilingual tasks, and workloads that benefit from a wide selection of price/performance tiers.
Qwen 3.5 Flash is one of the cheapest reasoning-capable models available — at 0.06/0.06/0.24 per MTok with 1M context, it’s significantly cheaper than DeepSeek V4 Flash while still supporting full reasoning modes. Great for high-volume tasks where cost matters.

​
Getting an API Key

  1. Go to qwencloud.com
  2. Sign up or log in
  3. Navigate to API Keys and create a new key
  4. Paste it into Wolffish → Settings → Models → Qwen

​
Models

​
Reasoning modes

The brain icon next to the message box controls how this model reasons. Click it to cycle through the modes the selected model supports. Two separate ideas combine here:

​
Thinking — whether the model reasons

  • Off — the model answers immediately. Fastest and cheapest; ideal for simple, direct tasks.
  • On — the model first works through the problem in a dedicated reasoning pass before replying. Slower and uses more tokens, but markedly more accurate on multi-step, logical, or ambiguous tasks.

​
Effort — how hard it thinks

Only effort-capable models expose this; it applies once thinking is on.
  • High — standard reasoning depth. The right default for most agentic work.
  • Max — the model reasons longer and deeper for the hardest problems. More tokens and latency in exchange for higher quality on complex work.

​
Button states

Each model shows only the states it genuinely supports. If a model always reasons (can’t be turned off) or has no effort control, the button reflects that and locks where there’s nothing to change. Wolffish remembers your choice per model. On Qwen: qwen3.x models support Off / High / Max (effort via a thinking-token budget). qwq and qvq reason always-on (locked on). Legacy qwen-max/plus/turbo/flash don’t reason.

​
Cost Comparison

Qwen spans a wide price range, competing at every tier:
Start with Qwen 3.5 Flash for high-volume tasks, Qwen 3.7 Plus for general agentic work, or Qwen 3.8 Max when you need frontier reasoning or vision. The dedicated Qwen3 Coder Plus model is a good pick for code-heavy workflows at a budget price.