prices synced 2026-09-11

Qwen3.8 2.4T A95B (batch)

Alibaba · Released Aug 2026

Compare

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Alibaba with 95 billion active parameters from a 2.4 trillion total parameter pool, supporting text, image, and video inputs.

Strengths
The sparse MoE architecture enables strong performance on complex reasoning and multimodal tasks while maintaining computational efficiency through selective parameter activation.
Best for
Batch processing workloads requiring multimodal reasoning over long contexts where the efficiency gains from sparse activation justify processing latency.
Limitations
As an open-weight model, it lacks the optimizations and support guarantees of Qwen3.8 Max, and batch-only availability means it cannot serve real-time inference requests.

Input / 1M

$2.00

Output / 1M

$6.00

Cached input / 1M

$0.25

Context window

1.01M

Price history

Input (solid)Output (dashed)
Price per 1M tokens over timeOutput went from $6.00 to $6.00; Input went from $2.00 to $2.00 between Aug 2026 and Sep 2026.$0$2.00$4.00$6.00Output on 28 Aug 2026: $6.00Output on 29 Aug 2026: $6.25Output on 31 Aug 2026: $6.00Output on 1 Sep 2026: $6.25Output on 2 Sep 2026: $6.00Out $6.00Input on 28 Aug 2026: $2.00Input on 29 Aug 2026: $2.50Input on 31 Aug 2026: $2.00Input on 1 Sep 2026: $2.50Input on 2 Sep 2026: $2.00In $2.00Aug 2026Sep 2026

Price change

30d
in decreased 0.0% out decreased 0.0%
90d
in decreased 0.0% out decreased 0.0%
1y
in decreased 0.0% out decreased 0.0%
Since launch
in decreased 0.0% out decreased 0.0%

Snapshots

Effective Input Output Cached in Note Source
2 Sep 2026 $2.00 $6.00 $0.25 Imported from OpenRouter openrouter.ai
1 Sep 2026 $2.50 $6.25 $0.5 Imported from OpenRouter openrouter.ai
31 Aug 2026 $2.00 $6.00 $0.25 Imported from OpenRouter openrouter.ai
29 Aug 2026 $2.50 $6.25 $0.5 Imported from OpenRouter openrouter.ai
28 Aug 2026 $2.00 $6.00 $0.25 Imported from OpenRouter openrouter.ai

More from Alibaba

Report a problem