Back to approved modelsrelay/request.mjsready to route CONTEXTN/Aprompt window MAX OUTPUTN/Aper response INPUT$0.25 / Mtoken price OUTPUT$1.5 / Mtoken price
Approved model profile_
Googleactive
Gemini 3.1 Flash-Lite Preview
Gemini 3.1 Flash-Lite Preview is available through the PipeLLM Model Router.
gemini-3.1-flash-lite-previewconst completion = await client.chat.completions.create({
model: "gemini-3.1-flash-lite-preview",
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./geminigemini-3.1-flash-lite-previewUse this in every requestPROVIDER AVAILABILITY1 route
| Provider | Context | Max output | Input / M | Output / M |
|---|---|---|---|---|
| Vertex AI | N/A | N/A | $0.25 / M | $1.5 / M |
SUPPORTED SURFACESactive
input: textoutput: text
Relay governs model access with the same routing policy that Lens keeps visible and auditable.