AI model
qwen/qwen3.8-2.4t-a95b
Qwen: Qwen3.8 2.4T A95B is a 1,048,576-token model served on Composite at $2.50 per million tokens in and $7.50 per million tokens out.
Try in Playground| Model ID | qwen/qwen3.8-2.4t-a95b |
|---|---|
| Provider | cv11 |
| Context window | 1,048,576 tokens |
| Accepts | text |
| Returns | text |
| Input price | $2.50 per million tokens |
| Output price | $7.50 per million tokens |
| Prompt caching | Supported — cached input is billed at the provider's cache rate, on credits and plans alike |
| Thinking | Always on for this model |
| Moderated | No |
| Cost on a monthly plan | About 22 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 10 (base plus 9 routing variants) |
Make a Composite API key and type qwen/qwen3.8-2.4t-a95b as the model name. JanitorAI takes the full URL https://composite.lucidity.sh/v1/chat/completions; SillyTavern, ChubAI, Agnai and RisuAI take https://composite.lucidity.sh/v1. It runs on credits, a plan, or your own provider key.
JanitorAI setup · SillyTavern setup · Best Janitor AI proxies compared
This model has not carried enough traffic on Composite yet to publish a success rate, a latency figure or a traffic rank. The numbers appear here once it has.
The same model behind 9 alternative endpoints. Call the id directly to pin a route; the base id above picks for you.
| Route | Model ID | Provider | Price |
|---|---|---|---|
| Normal | qwen/qwen3.8-2.4t-a95b-normal |
cv11 | $2.50 per million tokens input · $7.50 per million tokens output |
| Normal + cheapThink | qwen/qwen3.8-2.4t-a95b-normal:cheapThink |
cv11 | $2.50 per million tokens input · $7.50 per million tokens output |
| Cheapest provider | qwen/qwen3.8-2.4t-a95b:cheapest-provider |
Novita | $2.50 per million tokens input · $7.50 per million tokens output |
| Cheapest provider + cheapThink | qwen/qwen3.8-2.4t-a95b:cheapest-provider:cheapThink |
Novita | $2.50 per million tokens input · $7.50 per million tokens output |
| cheapThink | qwen/qwen3.8-2.4t-a95b:cheapThink |
cv11 | $2.50 per million tokens input · $7.50 per million tokens output |
| Fast | qwen/qwen3.8-2.4t-a95b:fast |
Novita | $2.50 per million tokens input · $7.50 per million tokens output |
| Fast + cheapThink | qwen/qwen3.8-2.4t-a95b:fast:cheapThink |
Novita | $2.50 per million tokens input · $7.50 per million tokens output |
| Quality | qwen/qwen3.8-2.4t-a95b:quality |
SiliconFlow | $2.50 per million tokens input · $7.50 per million tokens output |
| Quality + cheapThink | qwen/qwen3.8-2.4t-a95b:quality:cheapThink |
SiliconFlow | $2.50 per million tokens input · $7.50 per million tokens output |
$2.50 per million tokens input · $7.50 per million tokens output
Credits pay the provider’s price plus 25%; cache hits cost less.
On a monthly plan, a typical call (8k tokens in, 1k out) uses about 22 plan credits, at the provider's own price.
cv11
Qwen models pair large context windows with solid multilingual ability, useful for roleplay that switches languages or references long lore documents.
With a 1,048,576-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.
It sits in the mid-range on price, a reasonable pick for regular roleplay use without going for the cheapest option available.
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...
Supplied by cv11, not written by Composite.
Qwen: Qwen3.8 Max Prime · Qwen: Qwen3.8 Omni Flash · Qwen: Qwen3.8 Max (0902)