Voyage 轻量 embedding, 低成本 (1024 维, 32K context)
Model ID: voyage-4-lite · Type: embedding · Provider: Voyage
Endpoints: /v1/embeddings
| Input (per 1M tokens) | $0.02 USD |
from openai import OpenAI
client = OpenAI(api_key="sk-...", base_url="https://api.router.ai/v1")
resp = client.embeddings.create(model="voyage-4-lite", input="hello world")
print(len(resp.data[0].embedding))Voyage 4 Lite (`voyage-4-lite`) is billed per usage at $0.02 / 1M tokens in · None / 1M tokens out, in USD. Current pricing is always listed at https://ai-zzz.com/models/voyage-4-lite.
Send a request to https://api.router.ai/v1/v1/embeddings with the header `Authorization: Bearer <your API key>` and `"model": "voyage-4-lite"`. The API is OpenAI-compatible, so any OpenAI SDK works by changing base_url to https://api.router.ai/v1 — no other code change.
Voyage 4 Lite accepts up to 32,000 input tokens. Requests exceeding the input limit are rejected before reaching the model.
Voyage 4 Lite is a embedding model from Voyage, available through the AI中转站 gateway with the same API key as every other model.
Call it through the AI中转站 OpenAI-compatible endpoint (API base: https://api.router.ai/v1). AI agents can discover and call every model on this gateway through MCP (https://mcp.router.ai/mcp) with no manual integration.