Qwen3.5 122B A10B (Non-reasoning)
AI model by Alibaba. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Qwen3.5 122B A10B (Non-reasoning) is a budget-tier option from Alibaba at $3.20/M output tokens. Despite the low price, it scores competitively on Coding Index (43.3) and Intelligence Index (28.2) — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, Qwen3.5 122B A10B (Non-reasoning) reports 144 tok/s output speed and 2320ms time-to-first-token. Output speed is in the normal range — most chat and completion applications will be token-bound, not streaming-bound.
Cost model. For a workload of 1M input tokens + 100K output tokens, Qwen3.5 122B A10B (Non-reasoning) costs $0.72 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 2026-09-06.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Qwen3.5 122B A10B (Non-reasoning)Current | $0.40 | $3.20 | 144 tok/s |
| GLM-5 (Reasoning) | $1.00 | $3.20 | 66 tok/s |
| Nova Pro | $0.80 | $3.20 | — |
| GLM-5 (Non-reasoning) | $1.00 | $3.20 | 69 tok/s |
| Apodex 1.1 | $0.30 | $3.00 | — |
| Gemini 3 Flash Preview (Non-reasoning) | $0.50 | $3.00 | 187 tok/s |