Qwen3.8 2.4T A95B pricing & benchmarks
Qwen3.8 2.4T A95B is available from Alibaba at $2.00 per million input tokens and $6.00 per million output tokens ($3.00 blended at 3:1). It accepts up to 1,048,576 tokens of context. 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...
Pricing
Per million tokens · OpenRouter
Input$2.00
Output$6.00
Blended (3:1)$3.00
Specification
qwen/qwen3.8-2.4t-a95b
Context window1.0M
Max output909K
ReleasedAug 2026
LicenceOpen weights
Modalitiesin:text, out:text
No independently-run benchmark scores are published for Qwen3.8 2.4T A95B yet. We show nothing rather than reprinting an unverified figure.
Where to run Qwen3.8 2.4T A95B
5 hosts · all priced within ~5% of each other. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| Novita | $3.00 | $2.00 / $6.00 | 1M | — | 100.0% |
| Alibaba | $3.00 | $2.00 / $6.00 | 1M | — | 92.5% |
| SiliconFlow | $3.00 | $2.00 / $6.00 | 1.0M | fp8 | 100.0% |
| Venice ⚠ 262K context, not 1.0M |
$3.00 | $2.00 / $6.00 | 262K | — | 99.0% |
| Together | $3.00 | $2.00 / $6.00 | 1.0M | — | 99.9% |
Host prices and uptime from OpenRouter, synced 2026-10-22. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare Qwen3.8 2.4T A95B
FAQ
How much does Qwen3.8 2.4T A95B cost?
Qwen3.8 2.4T A95B costs $2.00 per million input tokens and $6.00 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $3.00 per million tokens.
What is Qwen3.8 2.4T A95B's context window?
Qwen3.8 2.4T A95B accepts up to 1,048,576 tokens of context, and can generate up to 909,000 output tokens.