Home › VastLLM Catalog › Qwen3.6 Flash
Qwen3.6 Flash
by Alibaba(Qwen) · Language Models
Context 1M tokensReasoning / thinking
by Alibaba(Qwen) · Language Models
Qwen3.6-Flash is the speed-optimized, cost-efficient tier of Alibaba's Qwen3.6 model family, reported as released in late April 2026 for high-throughput, low-latency inference. It is reported to support text, image and video input with a 1M-token context window, plus tool use and function calling. Third-party listings put its pricing near $0.19 per million input tokens and $1.13 per million output tokens, though these figures should be confirmed against official Model Studio pricing. Ideal for high-volume pipelines, classification, routing and latency-sensitive applications where flagship reasoning is not required.
$0.8547 in · $5.1295 out / 1M
| Usage | Rate (USD) | Unit |
|---|---|---|
| Input tokens | $0.85 | per 1M tokens |
| Cached input (cache hit) | $0.09 | per 1M tokens |
| Output tokens | $5.13 | per 1M tokens |
TuneRouter live platform 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": "qwen3.6-flash", "messages": [{"role": "user", "content": "Hello!"}]}'Model ID: qwen3.6-flash · works with OpenAI SDKs — just point base_url at api.tunerouter.com