Qwen3.5-35B-A3B
Alibaba · Multimodal · Released Feb 2026
A 35-billion-parameter multimodal model from Alibaba combining linear attention with sparse mixture-of-experts routing for efficient processing of text and images across a 262K token context window.
- Strengths
- Handles vision and language tasks within a single model while maintaining computational efficiency through its hybrid linear attention and sparse expert architecture.
- Best for
- Multimodal applications that need to process both text and images without the scale overhead of larger models like the 122B or 397B versions.
- Limitations
- The 262K token context is narrower than the 1M window available in newer Plus-tier models released the same month; for reasoning-heavy or code-focused work, Qwen3 Max Thinking or Qwen3 Coder Next may be more suitable.
Input / 1M
$0.14
Output / 1M
$1.00
Cached input / 1M
—
Context window
262K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in decreased 0.0% out decreased 0.0%
- 90d
- in decreased 0.0% out decreased 0.0%
- 1y
- in decreased 0.0% out decreased 0.0%
- Since launch
- in decreased 0.0% out decreased 0.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 28 Jul 2026 | $0.14 | $1.00 | — | Imported from OpenRouter | openrouter.ai |
| 15 Jul 2026 | $0.14 | $1.00 | — | Imported from OpenRouter | openrouter.ai |
| 25 Jun 2026 | $0.14 | $1.00 | $0.05 | Imported from OpenRouter | openrouter.ai |
| 19 Jun 2026 | $0.14 | $1.00 | — | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.14 | $1.00 | $0.05 | Imported from OpenRouter | openrouter.ai |