Qwen3.8 Max (0902)
Intelligence
45.44
#32 of 520 models
Output speed
37.6 tok/s
Measured generation rate
Cost / index task
$5.409
Measured evaluation workload
End-to-end latency
69ms
First answer 56ms
01 / Position
A model in the landscape
Compare this model with peers across intelligence, speed, cost, and individual evaluations.
02 / Evidence
Benchmark results
21 distinct evaluations grouped by topic. Explore cross-model charts or switch to the full results list.
Domain capability
03 / Operation
Speed, tokens & price
Prices are per million tokens; latency and task costs describe the captured evaluation rather than a universal provider guarantee.
Token pricing
- Input / 1M
- $2.00
- Output / 1M
- $6.00
- Cache read / 1M
- $0.250
- Cache write / 1M
- —
- Cache-hit discount
- 87.5%
Response & usage
- Output speed
- 37.6 tok/s
- First chunk
- 3ms
- First answer
- 56ms
- Output / task
- 107.7k
- Reasoning / task
- 70.8k
Evaluation workload
- Canonical input
- 9.9B
- Canonical output
- 191.96M
- Answer / task
- 36.9k
- Index time / task
- 38.5m
- Run cost
- $4,934.79
By prompt type
| Prompt | Output speed | First chunk | First answer | End to end |
|---|---|---|---|---|
| Medium | 40.1 tok/s | 2ms | 52ms | 64ms |
| Long | 37.6 tok/s | 3ms | 56ms | 69ms |
| Hundred K | 39.7 tok/s | 9ms | 59ms | 72ms |
| Medium Parallel | 40.5 tok/s | 2ms | 51ms | 64ms |
04 / Access
License & availability
Recorded license
No license recorded
No direct license document is available in the captured record. Weight availability alone does not establish usage rights.
- Weight access
- Closed / unavailable
- Classification
- Proprietary
- Reasoning
- Yes
Routing and providers
- OpenRouter ID
- qwen/qwen3.8-max-0902
- Tokenizer
- Qwen
- Instruct type
- —
- Captured endpoints
- 1
| Provider | Quantization | Context | tok/s |
|---|---|---|---|
| Alibaba | unknown | 1M | — |
05 / Audit
Underlying fields
Inspect the captured model and routing records. Artificial Analysis destination links are omitted.