Qwen3.8 2.4T A95B API pricing
Qwen3.8 2.4T A95B by TensorX costs $2.50 per 1M input tokens and $6.00 per 1M output tokens (1M in + 1M out = $8.50).
- API model id
qwen/qwen3.8-2.4t-a95b- Input / 1M
- $2.50
- Output / 1M
- $6.00
- Cached input / 1M
- $0.63
- Context window
- 256K
- Notes
- TensorX pay-as-you-go (EU, zero data retention), USD per 1M tokens.
- Source
- https://tensorx.ai/pricing
- Provider type
- Inference host (HQ: Ireland)
- Regions
- EU
- EU data residency
- yes — Pricing page: all inference on EU-sovereign infrastructure with zero data retention; 'EU data residency out of the box'. Dedicated clusters in Dublin, Helsinki and Paris regions. TensorX Ltd., Dublin, Ireland (formerly Tensorix).
- Last verified
- 2026-10-16
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| TensorX | Qwen3.8 2.4T A95B | $4.00 |
Uses standard list prices (no caching, batch or off-peak discounts). € and CHF rows are priced in that currency by the provider and not converted, so compare them with care.
Other TensorX models
- GLM-5.3: $1.75 / $4.50
- Kimi K3: $3.00 / $15.00
- GLM-5.3 Flash: $0.20 / $0.50
- DeepSeek V4.1 Flash: $0.50 / $1.50
- DeepSeek V4 Pro 0813: $2.00 / $4.00
- DeepSeek V4 Flash 0731: $0.25 / $0.30
- GLM-5.2: $1.50 / $4.50
- Qwen3.8 27B: $0.40 / $2.40