Deepinfra
100.00%Context256K
Max output131.1K
p50 latency1,478 ms
Throughput57.0 t/s
Input price$1.65
Output price$4.95
Zero retentionNo trainingCaching
Model directory
Baseer model profileLanguage model
alibaba/qwen3.8-2.4t-a95b
Qwen3.8 2.4T A95B
Open-weights release of the Qwen3.8 flagship (2.4T MoE, ~95B active); thinking always on with reasoning_effort low/medium/xhigh. The hosted Qwen 3.8 Max (vision, non-thinking, 1M default context) is Alibaba-only.
Input / 1M tokens$1.65
Output / 1M tokens$4.95
Maximum context262.1K
Inference providers6
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
Fireworks
100.00%Context262.1K
Max output128K
p50 latency1,101 ms
Throughput149.0 t/s
Input price$2
Output price$6
Zero retentionNo trainingCaching
Gmicloud
98.66%Context262.1K
Max output131.1K
p50 latency1,642 ms
Throughput62.0 t/s
Input price$2
Output price$6
Caching
Modal
100.00%Context262.1K
Max output131.1K
p50 latency362 ms
Throughput—
Input price$2
Output price$6
Zero retentionNo trainingCaching
Novita
99.94%Context262.1K
Max output131.1K
p50 latency1,646 ms
Throughput63.0 t/s
Input price$2
Output price$6
No trainingCaching
Togetherai
100.00%Context256K
Max output128K
p50 latency275 ms
Throughput—
Input price$2.5
Output price$6.25
Zero retentionNo trainingCaching
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Deepinfra | 256K | 131.1K | 1,478 ms | 57.0 t/s | 100.000% | $1.65 | $4.95 | |
Fireworks | 262.1K | 128K | 1,101 ms | 149.0 t/s | 100.000% | $2 | $6 | |
Gmicloud | 262.1K | 131.1K | 1,642 ms | 62.0 t/s | 98.659% | $2 | $6 | |
Modal | 262.1K | 131.1K | 362 ms | — | 100.000% | $2 | $6 | |
Novita | 262.1K | 131.1K | 1,646 ms | 63.0 t/s | 99.937% | $2 | $6 | |
Togetherai | 256K | 128K | 275 ms | — | 100.000% | $2.5 | $6.25 |
What can this model do?
Available modalities and capabilities across inference providers.
TextAdvanced reasoningTool useAutomatic cachingVisionTools
Reasoning options
LowMediumXhigh
Technical profile
- Model type
- Language model
- Release date
- Aug 3, 2026
- Knowledge cutoff
- —
- Regions
- —
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
alibaba/qwen3.8-2.4t-a95bModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.