All models
Alibaba (Qwen)
Qwen3.8 2.4T A95B balancedruns locally
alibaba/qwen3-8-2-4t-a95b
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...
Input / 1M
$2.00
USD per million tokens
Output / 1M
$6.00
USD per million tokens
Est. cost / token
$0.000003
$3.00 per 1M, 3:1 mix
Context window
1.05M
max output 131K
Major features
Open weightsCachingReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding4
- reasoning4
- math4
- summarization4
- extraction4
- classification4
- chat4
- creative4
- translation4
- vision1
- long context5
- agentic4
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 1088 GB |
| Q3_K_M | fair | 1268 GB |
| Q4_K_Mrecommended | good | 1582 GB |
| Q5_K_M | very good | 1839 GB |
| Q6_K | excellent | 2119 GB |
| Q8_0 | near-lossless | 2742 GB |
| F16 | lossless | 5149 GB |
Estimates. Mixture-of-experts: memory covers all parameters; only the active ones are used per token, so it runs faster than its size suggests.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $2.00 | $6.00 | $0.25 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $2.00
- Output
- $6.00
- Cached input
- $0.25
- Blended (3:1)
- $3.00
Details
- Company
- Alibaba (Qwen)
- Version
- 3.8
- Family
- Qwen
- Released
- 2026-08-12
- Parameters
- 2.45T (95B active)
- Max output
- 131K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 21 min ago