Embedding 2

embedding-2 · 智谱 ChatGLM

A text vector model that converts input text information into vector representations so that, in conjunction with a vector database, it provides an external knowledge base for the large model, thereby improving the accuracy of the model’s reasoning.

API Pricing

Input$0.069 / 1M tokens
Output$0.069 / 1M tokens

Specifications

Context8K tokens
Modalitiestext

Frequently asked questions

What is Embedding 2?

A text vector model that converts input text information into vector representations so that, in conjunction with a vector database, it provides an external knowledge base for the large model, thereby improving the accuracy of the model’s reasoning.

What is the context length of Embedding 2?

Embedding 2 has a 8,000 token context window.

How much does Embedding 2 cost?

On AIHubMix, Embedding 2 costs $0.069 per million input tokens and $0.069 per million output tokens.

What modalities does Embedding 2 support?

Embedding 2 accepts text input.

How do I call Embedding 2 via API?

Embedding 2 is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to embedding-2 — no other code changes needed.

Who created Embedding 2?

Embedding 2 is developed by 智谱 ChatGLM. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

More models from 智谱 ChatGLM

See all Z.AI models →

Embedding 3

by 智谱 ChatGLM

A text vector model that converts input text into vector representations to work with a…

$0.069/1M in · $0.069/1M out
8,000 tokens context

Chatglm_lite

by 智谱 ChatGLM
$0.286/1M in · $0.286/1M out

Chatglm_pro

by 智谱 ChatGLM
$1.429/1M in · $1.429/1M out

Chatglm_std

by 智谱 ChatGLM
$0.714/1M in · $0.714/1M out

Chatglm_turbo

by 智谱 ChatGLM
$0.714/1M in · $0.714/1M out

Code Davinci Edit 001

by 智谱 ChatGLM
$20/1M in · $20/1M out

Use Embedding 2 via the AIHubMix unified API — one interface for every major LLM.