Model Terminal

Qwen3.5-Flash

Qwen3.5-Flash is a production-hosted, fast-inference model API from Alibaba's Qwen team, mapped to the Qwen3.5-35B-A3B open-weight family. It supports a 1M-token context window with native multimodal inputs (text, image, video) and tool/function calling, optimized for low-latency, high-throughput developer workloads. Source: supabase.

Value score
Not scored
Context
tokens
Max output
tokens
Price

Capability radar

Identity

Developer
Qwen
Openness
Modalities
Release
Knowledge cutoff
Deprecation
API docs

Benchmarks

No benchmark scores yet.

Compare nearby

Pricing

Input / 1M
Output / 1M
Speed