Qwen3.8 2.4T A95B
Qwen (Alibaba) · Open weights · 1M context · released Aug 12, 2026 · checked 10h ago
Ways to buy 7
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| Qwen (Alibaba) API The lab's own API · cached $0.25 | $2 | $6 | $2 / $6List price | $0.25 | List price |
 DeepInfrafp4 · cached $0.2 | $2 | $6 | $2 / $6Same as list | $0.2 | Same as list |
 ModalDefault region · cached $0.25 | $2 | $6 | $2 / $6Same as list | $0.25 | Same as list |
 Novita AIDefault region · cached $0.25 | $2 | $6 | $2 / $6Same as list | $0.25 | Same as list |
 SiliconFlowfp8 · cached $0.25 | $2 | $6 | $2 / $6Same as list | $0.25 | Same as list |
 Together AIDefault region · cached $0.25 | $2 | $6 | $2 / $6Same as list | $0.25 | Same as list |
 VeniceDefault region · cached $0.25 | $2 | $6 | $2 / $6Same as list | $0.25 | Same as list |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $320.00 direct.
Helicone$320.00+0%
Kong AI Gateway$320.00+0%
LiteLLM$320.00+0%
Neon AI Gateway$320.00+0%
Vercel AI Gateway$320.00+0%
Cloudflare AI Gateway$336.00+5%
Requesty$336.00+5%
Eden AI$337.60+5.5%
OpenRouter$337.60+5.5%
No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
| Qwen3.8 Max Prime Qwen (Alibaba) · 1M | $4 | $12 | $4 / $12 | $6 | 1M | Lab list price | · |
| Qwen3.8 Omni Flash Qwen (Alibaba) · 1M | $0.15 | $0.47 | $0.15 / $0.47 | $0.23 | 1M | Lab list price | · |
| Qwen3.8 Max (0902) Qwen (Alibaba) · 1M | $2 | $6 | $2 / $6 | $3 | 1M | Lab list price | · |
| Qwen3.8 Flash Qwen (Alibaba) · 1M | $0.15 | $0.47 | $0.15 / $0.47 | $0.23 | 1M | Lab list price | · |
 GPT-5.6 SolOpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · |
 Muse Spark 1.3Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · |
 Gemini 3.8 FlashGoogle · 1MCheapest: $0.75 on Google Gemini API (flex) | $0.75 | $3.75 | $0.75 / $3.75 | $1.5 | 1M | $0.75 on Google Gemini API (flex) | · |
| Gemini 3.1 Pro Preview Google · 1MCheapest: $2.25 on Google Vertex AI (global-flex) | $2 | $12 | $2 / $12 | $4.5 | 1M | $2.25 on Google Vertex AI (global-flex) | · |
About 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.
Takes text in and returns text. First listed Sep 23, 2026. Up to 131K output tokens. Blended price $3 per 1M tokens at 3 input to 1 output. Overall score 5 on leadersboard.fru.dev (rank 27). Model id qwen3-8-2-4t-a95b.
Price history
List price since Sep 23, 2026, from daily reads of the OpenRouter catalog.
Across fru.devCompany profile
Questions
How much does Qwen3.8 2.4T A95B cost?
$2 per million input tokens and $6 per million output tokens, with cached input at $0.25.
What is the context window of Qwen3.8 2.4T A95B?
1M tokens, with up to 131K tokens of output.
Where is Qwen3.8 2.4T A95B cheapest?
Of 7 routes tracked, DeepInfra is cheapest at $2 input and $6 output per million tokens.
Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.