Qwen3.8 2.4T A95B
The cheapest provider for Qwen3.8 2.4T A95B is Alibaba at $3.00 per 1M tokens (blended), charging $2.00 per 1M input and $6.00 per 1M output tokens. 7 providers serve it at the same price. Context window: 1M tokens. Prices tracked since Oct 3, 2026.
Best price
$3.00
at Alibaba
Input / output
$2.00 / $6.00
per 1M tokens
Providers
7
1.00× spread
7 days
—
best price
30 days
—
best price
Context
1M
tokens
Providers
Active offers ranked by blended price. Bars are relative to the most expensive.
| Provider | Input | Output | Blended | vs cheapest | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
AlibabaCheapest | $2.00 | $6.00 | $3.00 | best | |||
| fp4 | $2.00 | $6.00 | $3.00 | best | |||
| $2.00 | $6.00 | $3.00 | best | ||||
| $2.00 | $6.00 | $3.00 | best | ||||
| fp8 | $2.00 | $6.00 | $3.00 | best | |||
| $2.00 | $6.00 | $3.00 | best | ||||
| −20% discount | $2.00 | $6.00 | $3.00 | best |
- AlibabaCheapest$3.00$2.00 in · $6.00 outbest1M ctx99.9% uptime
- $3.00$2.00 in · $6.00 outbest256K ctx100% uptimefp4
- $3.00$2.00 in · $6.00 outbest1M ctx99.5% uptime
- $3.00$2.00 in · $6.00 outbest1M ctx99.9% uptime
- $3.00$2.00 in · $6.00 outbest1M ctx99.9% uptimefp8
- $3.00$2.00 in · $6.00 outbest1M ctx100% uptime
- $3.00$2.00 in · $6.00 outbest256K ctx98.5% uptime−20% discount
Blended = (3 × input + output) / 4.
Price history
Hover to compare providers at any point in time. Click a legend item to hide it.
USD per 1M tokens · each step is a price change
Not enough history yet
Tracking since Oct 3, 2026. The chart fills in as new crawls arrive every 6 hours.
Other pricing
Cache, reasoning and per-call fees. Token rates per 1M; others per unit.
| Offered by | Cache read | Cache write |
|---|---|---|
| Alibaba | $0.25 | $2.50 |
| DeepInfra | $0.20 | — |
| Modal, Novita +3 | $0.25 | — |
Change log
Every recorded change for this model since Oct 3, 2026.
No changes yet
Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.
About this model
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...
- Released
- Aug 12, 2026
- First tracked
- Oct 3, 2026
- Canonical slug
- qwen/qwen3.8-2.4t-a95b-20260812
- Weights
- Qwen/Qwen3.8-2.4T-A95B