Home › VastLLM Catalog › Qwen3.5 Flash
Qwen3.5 Flash
by Alibaba(Qwen) · Language Models
Context 1M tokensReasoning / thinking
by Alibaba(Qwen) · Language Models
Qwen3.5-Flash is the cost-optimized, lower-latency tier of Alibaba's Qwen3.5 series, reported as built on a 35B-A3B architecture for efficient inference. Like its Plus sibling it is natively multimodal, accepting text, image and video input, and reporting indicates it shares the family's 1M-token context window. It prioritizes throughput and price over the deeper reasoning of the Plus tier. Ideal for high-volume, latency-sensitive multimodal tasks such as quick visual understanding, routing and lightweight agent steps.
$0.1328 in · $1.3282 out · $0.0131 cached / 1M
| Usage | Rate (USD) | Unit |
|---|---|---|
| Input tokens | $0.1328 | per 1M tokens |
| Cached input (cache hit) | $0.0131 | per 1M tokens |
| Output tokens | $1.3282 | per 1M tokens |
Official model pricing · currency: USD · pre-deduction settled by actual usage
OpenAI-compatible · base URL https://api.tunerouter.com/v1/
curl https://api.tunerouter.com/v1/chat/completions \
-H "Authorization: Bearer $TUNEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "qwen3.5-flash", "messages": [{"role": "user", "content": "Hello!"}]}'Model ID: qwen3.5-flash · works with OpenAI SDKs — just point base_url at api.tunerouter.com