AlibabaQwen3.8 2.4T A95B
Not yet ranked: too few independent results so far. Released 12 Aug 2026.
- Blended price
- $3.00/M
- $2.00 in · $6.00 out
- Output speed
- 41 tok/s
- First answer
- 52 s
- first token 1.39 s
- Context
- 984k
- Knowledge66
- Long context67
- Composite79
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| GPQA Diamond (AA)not in index | 93.5%#14 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 42.5%#39 | Artificial Analysis |
Coding
| Benchmark | default | Source |
|---|---|---|
| SciCode (AA)not in index | 54.0%#42 | Artificial Analysis |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| AA-Omniscience | 4.3#76 | Artificial Analysis |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 80.3%#45 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 40.0#34 | Artificial Analysis |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Modal | 166 tok/s | 0.49 s | $2.00 | $6.00 | 1M | – |
| Together | 83 tok/s | 1.23 s | $2.00 | $6.00 | 1.0M | – |
| Venice | 72 tok/s | 1.10 s | $2.50 | $7.50 | 262k | – |
| DeepInfra | 62 tok/s | 1.39 s | $2.00 | $6.00 | 262k | fp4 |
| Alibaba Cloud Int. | 37 tok/s | 1.42 s | $2.00 | $6.00 | 1M | – |
| SiliconFlow | 33 tok/s | 1.62 s | $2.00 | $6.00 | 1.0M | fp8 |
| NovitaAI | 32 tok/s | 4.90 s | $2.00 | $6.00 | 1M | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.200 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0026 | $0.0021 | 59.3 s |
| Summarise a 30-page report | 12,000 / 600 | $0.028 | $0.011 | 1.1 min |
| Code edit | 6,000 / 1,500 | $0.021 | $0.013 | 1.5 min |
| Agentic coding session | 60,000 / 4,000 | $0.144 | $0.063 | 2.5 min |
| Structured extraction | 2,000 / 200 | $0.0052 | $0.0025 | 56.8 s |
See also
Data as of 9 Sept 2026. Compare with another model.