Qwen-Omni Turbo Realtime

by Alibaba · qwen family · released 2025-05-08

On output pricing, Qwen-Omni Turbo Realtime is cheaper than 370 of the 588 priced models tracked here, at $1.07/Mtok. Its 32,768-token context window is larger than 102 of 674 models. Capabilities: vision, tools.

Specifications

ProviderAlibaba
Familyqwen
Input price$0.27/Mtok
Output price$1.07/Mtok
Context window32,768
Max output tokens2,048
Input modalitiestext, image, audio
Output modalitiestext, audio
Capabilitiesvision, tools
Knowledge cutoff2024-04-01
Released2025-05-08

Estimate Qwen-Omni Turbo Realtime costs for your workload →

Similar models

Qwen3.7 Plus
Alibaba · $3/Mtok out · 1M context
Qwen3.7 Max
Alibaba · $7.5/Mtok out · 1M context
Qwen3.6 27B
Alibaba · $3.6/Mtok out · 262.1K context
Qwen3.6 Max Preview
Alibaba · $7.8/Mtok out · 262.1K context

Related reading

Gemini 3.5 Flash vs Qwen 3.7 Max for Indie Hackers in 2026 Qwen 3.7 Max vs Claude Sonnet 4.6 for Indie Hackers in 2026: The Frontier Model You Haven't Tried Yet
Alibaba documentation → ← All AI models

Data synced daily from models.dev (last synced 14 hours ago). Always verify pricing with Alibaba before deploying to production.