Back to approved modelsrelay/request.mjsready to route CONTEXT400K contextprompt window MAX OUTPUT128Kper response INPUT$1.3 / Mtoken price OUTPUT$10.0 / Mtoken price
Approved model profile_
OpenAIactive
GPT-5
GPT-5 is available through the PipeLLM Model Router.
gpt-5const completion = await client.chat.completions.create({
model: "gpt-5",
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./geminigpt-5Use this in every requestPROVIDER AVAILABILITY1 route
| Provider | Context | Max output | Input / M | Output / M |
|---|---|---|---|---|
| Azure | 400K context | 128K | $1.3 / M | $10.0 / M |
SUPPORTED SURFACESactive
input: textoutput: texttool usecache controlcomputer use
Relay governs model access with the same routing policy that Lens keeps visible and auditable.