Back to approved models
xAIactiverelay/request.mjsready to route CONTEXT500K contextprompt window MAX OUTPUTN/Aper response INPUT$2.0 / Mtoken price OUTPUT$6.0 / Mtoken price
Approved model profile_
xAIactiveGrok 4.5
Grok 4.5 is xAI's smartest model, with frontier performance across coding, knowledge work, and STEM.
grok-4.5const completion = await client.chat.completions.create({
model: "grok-4.5",
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./geminigrok-4.5Use this in every requestPROVIDER AVAILABILITY1 route
| Provider | Context | Max output | Discount | Input / M | Output / M |
|---|---|---|---|---|---|
| xAI | 500K context | N/A | — | $2.0 / M | $6.0 / M |
SUPPORTED SURFACESactive
input: textinput: imageinput: fileoutput: texttool usecache control
Relay governs model access with the same routing policy that Lens keeps visible and auditable.