Back to approved models
Anthropicactiverelay/request.mjsready to route CONTEXT1M contextprompt window MAX OUTPUT128Kper response INPUT$5.0 / Mtoken price OUTPUT$25.0 / Mtoken price
Approved model profile_
Claude Opus 4.8
Claude Opus 4.8 is Anthropic’s frontier Opus model for complex reasoning, software engineering, multimodal analysis, and long-running agent workflows. It supports extended context, high-output tasks, tool use, and cache-aware workflows, making it suitable for demanding research, coding, and...
claude-opus-4-8const completion = await client.chat.completions.create({
model: "claude-opus-4-8",
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.ai/openaiOpenAI-compatible routeclaude-opus-4-8Use this in every requestPROVIDER AVAILABILITY2 routes
| Provider | Context | Max output | Input / M | Output / M |
|---|---|---|---|---|
| AWS | 1M context | 128K | $5.0 / M | $25.0 / M |
| GCP Vertex | 1M context | 128K | $5.0 / M | $25.0 / 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.
