Gemini 多模态嵌入 (文本/图/音频/视频)
Model ID: gemini-embedding-2-preview · Type: embedding · Provider: Google
Endpoints: /v1/embeddings
| Input (per 1M tokens) | $0.15 USD |
from openai import OpenAI
client = OpenAI(api_key="sk-...", base_url="https://api.router.ai/v1")
resp = client.embeddings.create(model="gemini-embedding-2-preview", input="hello world")
print(len(resp.data[0].embedding))Gemini Embedding 2 Preview (`gemini-embedding-2-preview`) is billed per usage at $0.20 / 1M tokens in · None / 1M tokens out, in USD. Current pricing is always listed at https://openbat.ai/models/gemini-embedding-2-preview.
Send a request to https://api.router.ai/v1/v1/embeddings with the header `Authorization: Bearer <your API key>` and `"model": "gemini-embedding-2-preview"`. The API is OpenAI-compatible, so any OpenAI SDK works by changing base_url to https://api.router.ai/v1 — no other code change.
Gemini Embedding 2 Preview accepts up to 8,192 input tokens and can return up to 8,192 output tokens. Requests exceeding the input limit are rejected before reaching the model.
Gemini Embedding 2 Preview supports: multimodal.
Gemini Embedding 2 Preview is a embedding model from Google, available through the openbat.ai gateway with the same API key as every other model.
Call it through the openbat.ai 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.