OpenRouter adds Qwen 3.5 Plus (1M context, low-cost chat model)
TL;DR
OpenRouter adds Alibaba's Qwen3.5 Plus multimodal model with 1M token context. It processes text, image, and video inputs at $0.40 per million input tokens and $2.40 per million output tokens.
What changed
OpenRouter now offers Qwen3.5 Plus 2026-04-20 from Alibaba. This multimodal model processes text, image, and video inputs to generate text output with a 1 million token context window. It prices at $0.40 per million input tokens and $2.40 per million output tokens.
Why it matters
Developers get affordable access to high-context multimodal AI for building apps. Basic users can route prompts with images or videos through OpenRouter. Vibe builders find new tools for creative content generation.
What to watch for
Check early benchmarks on multimodal tasks against rivals. Watch OpenRouter stats for adoption rates. Look for community fine-tunes or API integrations soon.
Who this matters for
- Vibe Builders: Use the 1M context window to feed entire video libraries into the model for creative synthesis.
- Developers: Integrate this multimodal model via OpenRouter to lower costs for high-volume video analysis tasks.
What to watch next
Alibaba continues to push aggressive pricing that forces Western providers to justify their premiums. By dropping a 1M context window at these rates, they effectively commoditize long-context multimodal processing. Most teams currently overpay for similar capabilities on proprietary platforms without seeing a proportional increase in output quality.
This release makes high-context applications financially viable for startups that previously lacked the budget for massive token consumption. OpenRouter remains the smartest way to deploy these models without vendor lock-in. Relying on a single provider for multimodal tasks is a strategic error when the landscape shifts this quickly.
Developers should treat this model as a drop-in replacement for expensive incumbents to immediately slash operational overhead. If your current pipeline does not utilize this price point, you are burning capital on legacy infrastructure.
by Harsh Desai