Qwen3.5 397B A17B (Non-reasoning)
AI model by Alibaba. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Qwen3.5 397B A17B (Non-reasoning) is a budget-tier option from Alibaba at $3.60/M output tokens. Despite the low price, it scores competitively on measurable benchmarks — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, Qwen3.5 397B A17B (Non-reasoning) reports 83 tok/s output speed and 2040ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.
Cost model. For a workload of 1M input tokens + 100K output tokens, Qwen3.5 397B A17B (Non-reasoning) costs $0.96 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Qwen3.5 397B A17B (Non-reasoning)Current | $0.60 | $3.60 | 83 tok/s |
| Gemini 3.6 Flash (high) | $0.75 | $3.75 | 222 tok/s |
| Gemini 3.7 Flash (high) | $0.75 | $3.75 | 323 tok/s |
| Gemini 3.7 Flash (low) | $0.75 | $3.75 | 303 tok/s |
| Gemini 3.7 Flash (medium) | $0.75 | $3.75 | 317 tok/s |
| DeepSeek V4 Pro 0813 (Reasoning, Max Effort) | $1.32 | $3.96 | 74 tok/s |