Qwen2.5 Turbo
AI model by Alibaba. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Qwen2.5 Turbo is a budget-tier option from Alibaba at $0.20/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, Qwen2.5 Turbo reports 108 tok/s output speed and 2160ms 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, Qwen2.5 Turbo costs $0.07 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 |
|---|---|---|---|
Qwen2.5 TurboCurrent | $0.05 | $0.20 | 108 tok/s |
| gpt-oss-20b (low) | $0.07 | $0.20 | 170 tok/s |
| NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) | $0.05 | $0.20 | 225 tok/s |
| NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | $0.05 | $0.20 | 168 tok/s |
| Ministral 3 14B | $0.20 | $0.20 | 85 tok/s |
| NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | $0.05 | $0.20 | 261 tok/s |