AI model
qwen/qwen3.8-27b
Qwen: Qwen3.8 27B is a 1,048,575-token model served on Composite at $0.0775 per million tokens in and $0.549 per million tokens out. Ranked #81 of 179 models by traffic on Composite over the last 30 days, taking 0.03% of tokens and 0.02% of requests (this model and its routing variants).
Try in Playground| Model ID | qwen/qwen3.8-27b |
|---|---|
| Provider | cv11 |
| Context window | 1,048,575 tokens |
| Accepts | text, image, video |
| Returns | text |
| Input price | $0.0775 per million tokens |
| Output price | $0.549 per million tokens |
| Prompt caching | Supported — cached input is billed at the provider's cache rate, on credits and plans alike |
| Thinking | Optional - see "Qwen: Qwen3.8 27B (Reasoning)" in the catalog to turn it on by default |
| Moderated | No |
| Cost on a monthly plan | About 0.9 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/qwen3.8-27b 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
#81 of 179
0.03% of tokens and 0.02% of requests over 30 days, including routing variants.
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/qwen3.8-27b-normal |
cv11 | $0.188 per million tokens input · $2.34 per million tokens output |
| Normal + cheapThink | qwen/qwen3.8-27b-normal:cheapThink |
cv11 | $0.188 per million tokens input · $2.34 per million tokens output |
| Cheapest provider | qwen/qwen3.8-27b:cheapest-provider |
PrimeIntellect | $0.0775 per million tokens input · $0.549 per million tokens output |
| Cheapest provider + cheapThink | qwen/qwen3.8-27b:cheapest-provider:cheapThink |
PrimeIntellect | $0.0775 per million tokens input · $0.549 per million tokens output |
| cheapThink | qwen/qwen3.8-27b:cheapThink |
cv11 | $0.0775 per million tokens input · $0.549 per million tokens output |
| Fast | qwen/qwen3.8-27b:fast |
PrimeIntellect | $0.0775 per million tokens input · $0.549 per million tokens output |
| Fast + cheapThink | qwen/qwen3.8-27b:fast:cheapThink |
PrimeIntellect | $0.0775 per million tokens input · $0.549 per million tokens output |
| Quality | qwen/qwen3.8-27b:quality |
GMICloud | $0.563 per million tokens input · $4.00 per million tokens output |
| Quality + cheapThink | qwen/qwen3.8-27b:quality:cheapThink |
GMICloud | $0.563 per million tokens input · $4.00 per million tokens output |
$0.0775 per million tokens input · $0.549 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 0.9 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 1,048,575-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 is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.
Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...
Supplied by cv11, not written by Composite.
Qwen: Qwen3.8 Max Prime · Qwen: Qwen3.8 Omni Flash · Qwen: Qwen3.8 Max (0902)