Qwen Audio Realtime Tested: Cost and Reasoning vs GPT Models
ArtificialAnlys · x · 2026-07-29
Artificial Analysis has released a new comparison of native Speech-to-Speech models. On the Big Bench Audio subset, Qwen Audio 3.0 Realtime Plus costs $4.42 per hour of input audio—slightly more expensive than GPT-Realtime-2 High ($4.14) but 2.4x cheaper than GPT-Realtime-2.1 High ($10.75).
Meanwhile, the Flash variant measures $4.77 per hour, appearing more costly than Plus on the benchmark. This is driven by comparatively more verbose responses: Flash generates an average of 2,043 total output tokens per response versus 1,232 for Plus.
Related event: Qwen Audio 3.0 Realtime Costs Slightly Higher Than GPT in Benchmark(2 posts)→
More from Models
- Claude Code adds idle compaction to save 1h prompt cache on idle sessions — EricBuess · 2026-10-16
- Thrive Holdings launches real-work AI evals from 75+ businesses, benchmarking 13 models — samaysham · 2026-10-16
- Microsoft's MAI-Transcribe now handles 61% of all transcription on OpenRouter — mustafasuleyman · 2026-10-16
- Reflection AI Releases Open-Weight 501B MoE Beam for Agentic Coding on AWS — AWS ML Blog · 2026-10-16
- Dev RL-tunes Qwen 27B against slop with Meta's XAR method, lands top-4 on EQbench — Mysterious_Hearing14 · 2026-10-16
- HotDogBench tests 10 LLMs on 1,000 hot dog photos — all within each other's error bars — josh_wills · 2026-10-16