qwen/qwen3.8-27b
Model weightsQwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be enabled or disabled.
Not currently available through EU in-region routing. In-region routing docs
| $0.20 | $2.50 | $0.09 | -- | -- | 0.34s | 152 tps | ||
| $0.04 | $2.30 | $0.02 | -- | -- | 0.71s | 88 tps | ||
| $0.24 | $2.20 | $0.05 | -- | -- | 0.58s | 67 tps | ||
| $0.04 | $2.50 | $0.02 | -- | -- | 1.03s | 72 tps | ||
| $0.225 | $1.98 | $0.05 | -- | -- | 0.64s | 42 tps | ||
| $0.02 | $0.50 | $0.009 | -- | -- | 1.78s | 28 tps | ||
 25% off | $0.20$0.15 | $2.50$1.875 | $0.05$0.0375 | -- | -- | 1.04s | 33 tps | |
| $0.99 | $1.49 | $0.99 | -- | -- | 0.21s | 559 tps | ||
| $0.18 | $2.50 | -- | -- | -- | 1.05s | 36 tps | ||
| $0.039 | $1.25 | $0.0039 | -- | -- | 3.58s | 26 tps | ||
| $0.04 | $2.20 | $0.02 | -- | -- | 1.85s | 28 tps | ||
| $0.035 | $2.20 | $0.0175 | -- | -- | 1.77s | 17 tps | ||
| $0.45 | $3.20 | -- | -- | -- | 1.34s | 80 tps | ||
| $0.42 | $3.00 | $0.085 | -- | -- | 6.57s | 37 tps | ||
| $0.45 | $3.20 | $0.05 | -- | -- | 0.40s | 40 tps | ||
| $0.04 | $1.35 | $0.018 | -- | -- | 1.19s | 100 tps | ||
| $0.40 | $3.00 | $0.15 | -- | -- | 0.44s | 54 tps | ||
| $0.06 | $2.30 | $0.059 | -- | -- | 0.50s | 34 tps | ||
| $0.04 | $1.95 | $0.02 | -- | -- | 0.61s | 53 tps | ||
| $0.425 | $2.55 | $0.085 | $0.53125 | $0.0425 | 1.96s | 40 tps | ||
| $0.20 | $2.50 | $0.05 | -- | -- | 9.61s | 34 tps |
P50, best across providers
P50, best provider
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.
