alibaba
Qwen3.8 Max 0902
Qwen3.8-Max-0902 is an upgraded snapshot of qwen3.8-max.
reasoningtool usevisionfile inputimplicit cachingexplicit cachingstructured outputtextimagepdf
Overview
- Type
- language
- Context
- 991K
- Max output
- 128K
- Input / output
- text, image, pdf / text
API
Model identifier
alibaba/qwen3.8-max-0902Providers and live performance
Rolling Gateway metrics. Latency is time to first token; throughput is output tokens per second.
| Provider | Status | Latency | Throughput | Uptime 15m / 1h / 1d | Input | Output | Cache read / write | Discount | Regions | ZDR | No training |
|---|---|---|---|---|---|---|---|---|---|---|---|
| alibaba | Operational | 1.39s / 2.18s | 42.5 / 64.8 tok/s | 100.00% / 100.00% / 99.99% | $2.00/M | $6.00/M | $0.25/M / $2.50/M | — | — | Yes | Yes |
Pricing
input
0.000002
output
0.000006
input cache read
0.00000025
input cache write
0.0000025
Capabilities
reasoningtool usevisionfile inputimplicit cachingexplicit cachingstructured outputtextimagepdf
Supported parameters
max tokens
Yes
temperature
Yes
stop
Yes
tools
Yes
tool choice
Yes
reasoning
Yes
include reasoning
Yes
response format
Yes
structured outputs
Yes
Reasoning options
options
{
"type": "toggle"
}, {
"type": "effort",
"values": [
"low",
"medium",
"xhigh"
]
}, {
"type": "budget_tokens",
"min": 0,
"max": 262144
}
Metadata
type
language
context window
991K
max output
128K
released
Sep 1, 2026
temperature control
Yes
zero data retention
all
no training
all
api specifications
v2, v3, v4