- Models
- 6
- listed and live
- Location
- Non-EU
- where requests are served
- Trains on prompts
- Not declared
- nothing published yet
- Keeps prompts
- Not declared
- nothing published yet
Models
What Alibaba serves on llm.buzz, at its own prices.
| Model | Input | Output | Cache read | Context | Latency | Uptime (3d) |
|---|---|---|---|---|---|---|
 moonshotai/kimi-k3 | $3.45 | $17.25 | $0.345 | 1M | 1.44 s | 100% |
 qwen/qwen-image-3 | n/a | $0.03/image | n/a | n/a | n/a | n/a |
qwen/qwen3.8-flash | $0.15 | $0.47 | $0.016 | 1M | 1.44 s | 100% |
qwen/qwen3.8-max-0902 | $2.00 | $6.00 | $0.25 | 1M | 1.72 s | 100% |
qwen/qwen3.8-omni-flash | $0.15 | $0.47 | $0.016 | 1M | 2.07 s | 98.6% |
 z-ai/glm-5.3 | $1.19 | $3.74 | $0.238 | 1M | 1.72 s | 100% |
Alibaba's own prices, in USD per million tokens unless a price names another unit. Latency is the median time to first token over 24 hours.
Call Alibaba's models with one keyThe same key reaches every provider here; each request pays the price of the provider that answered it.