Qwen: Qwen3.8 2.4T A95B
standardqwen/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...
AA INDEX39.9
CONTEXT1049K
MODALITYtext->text
OPENNESSProprietary
ADDEDAug 2026
LAST PRICED20 min ago
Input
$2.00 /M
Output
$6.00 /M
Blended (40/60)
$4.40 /M
Cost / IQ
$4.4059 /M
Cost / IQ = Blended Price ÷ (AA Intelligence Score ÷ 40). Normalises price by model intelligence so you can compare value across tiers. Lower = better value per unit of intelligence. Not a transactional price.
24h0%
7d0%
Price History
30-day view, daily close
Low: $4.40/M
High: $4.40/M
Average: $4.40/M
Pricing Variants
Cached Input
$0.25/M
87.5% cheaper than standard
Batch (async)
$4.40/M
0% cheaper than standard
In: $2.00/M · Out: $6.00/M
Provider Comparison
6 providers · click a column to sort
| Provider | Input $/M | Output $/M | Blended $/M ↑ | vs Median |
|---|---|---|---|---|
| ↓Alibaba | $2.00 | $6.00 | $4.40 | median |
| Novita | $2.00 | $6.00 | $4.40 | median |
| SiliconFlow | $2.00 | $6.00 | $4.40 | median |
| Together | $2.00 | $6.00 | $4.40 | median |
| Venice | $2.00 | $6.00 | $4.40 | median |
| TensorX | $2.50 | $6.00 | $4.60 | +4.5% |
Blended price = 40% input + 60% output. Median price shown in header is the reference price for this model.
Cost / IQ Comparison
Cost / IQ (quality-adjusted $/M)$4.4059/M
Cost per GPT-4-equivalent token. Lower = better value. Comparable across all models.
287.7% above SIT TPI
Value Ranking (by Cost / IQ)
Rank #128 of 148 standard models
← YOU ARE HERE | Qwen: Qwen3.8 2.4T A95B
Data Sources
Source
Aggregator & direct provider data
6 sources · updated recently
API Access
# Get this model's current price
curl https://api.inferenceindexer.ai/v1/models/qwen/qwen3.8-2.4t-a95b
# Response (truncated)
{ "model_id": "qwen/qwen3.8-2.4t-a95b", "name": "Qwen: Qwen3.8 2.4T A95B", "blended_price_per_m": 4.4, "sit_adjusted_price": 4.405929 }