Back to approved models
Qwenactiverelay/request.mjsready to route CONTEXT1M contextprompt window MAX OUTPUTN/Aper response INPUT$1.6 / Mtoken price OUTPUT$5.0 / Mtoken price
Approved model profile_
QwenactiveQwen3.8 Max 0902
Qwen3.8-Max-0902 is the September 2, 2026 snapshot of Alibaba's Qwen3.8-Max family. This revision focuses on complex software engineering, coordination across tools, and sustained agent execution. It also refines visual reasoning for charts, documents, and other multimodal material. The model is...
qwen3.8-max-0902const completion = await client.chat.completions.create({
model: "qwen3.8-max-0902",
messages: [
{ role: "user",
content: "Plan a multi-step task" }
]
});Route configuration_
Use the model through the contract you already have.
PipeLLM resolves provider access, policy, and supported model capabilities without changing the interface your application calls.
https://api.pipellm.aiOne base URL for OpenAI, Anthropic, and Gemini.FORMAT ROUTES
OPENAI
/openaiANTHROPIC
/anthropicGEMINI
Use a format route to normalize requests and responses./geminiqwen3.8-max-0902Use this in every requestPROVIDER AVAILABILITY1 route
| Provider | Context | Max output | Discount | Input / M | Output / M |
|---|---|---|---|---|---|
| Alibaba-global | 1M context | N/A | — | $1.6 / M | $5.0 / M |
SUPPORTED SURFACESactive
input: textoutput: text
Relay governs model access with the same routing policy that Lens keeps visible and auditable.
