Model catalog

Embed v1 0.6b

perplexity/pplx-embed-v1-0.6b

Embedding

pplx-embed-v1 is a state-of-the-art text embedding model optimized for real-world, web-scale retrieval tasks.

Context

32K

In / 1M

$0.0040

Out / 1M

—

• open weights

Embed v1 4b

perplexity/pplx-embed-v1-4b

Embedding

pplx-embed-v1 is a state-of-the-art text embedding model optimized for real-world, web-scale retrieval tasks.

Context

32K

In / 1M

$0.030

Out / 1M

—

• open weights

Qwen3 Embedding 0.6B

alibaba/qwen3-embedding-0.6b

Embedding

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).

Context

33K

In / 1M

$0.010

Out / 1M

—

• open weights

Qwen3 Embedding 4B

alibaba/qwen3-embedding-4b

Embedding

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).

Context

33K

In / 1M

$0.020

Out / 1M

—

• open weights

Qwen3 Embedding 8B

alibaba/qwen3-embedding-8b

Embedding

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).

Context

33K

In / 1M

$0.010

Out / 1M

—

• open weights

Embed 5 Fast

cohere/embed-v5.0-fast

Embedding

Cohere's lightweight embedding model optimized for low latency and high throughput in interactive search, agent loops, and high-volume retrieval. Embed 5 Fast supports text, images, and mixed content, over 100 languages, and a 128,000-token context window, with output dimensions from 256 to 2,048. It shares an embedding space with Embed 5 Pro.

Context

128K

In / 1M

$0.080

Out / 1M

—

Embed 5 Pro

cohere/embed-v5.0-pro

Embedding

Cohere's most capable embedding model for quality-critical enterprise retrieval across text, images, and mixed content such as PDFs. Embed 5 Pro supports over 100 languages and a 128,000-token context window, with output dimensions from 256 to 2,048. It shares an embedding space with Embed 5 Fast, enabling Pro indexing with Fast querying.

Context

128K

In / 1M

$0.120

Out / 1M

—

Gemini Embedding 2

google/gemini-embedding-2

Embedding

Google’s first fully multimodal Embedding model that is capable of mapping text, image, video, audio, and PDFs and their interleaved combinations thereof into a single, unified vector space. Built on the Gemini architecture, it supports 100+ languages.

Context

—

In / 1M

$0.200

Out / 1M

—

Optimized for general-purpose and multilingual retrieval quality. All embeddings created with the 4 series are compatible with each other.

Context

32K

In / 1M

$0.060

Out / 1M

—

The best general-purpose and multilingual retrieval quality. All embeddings created with the 4 series are compatible with each other.

Context

32K

In / 1M

$0.120

Out / 1M

—

Optimized for latency and cost. All embeddings created with the 4 series are compatible with each other.

Context

32K

In / 1M

$0.020

Out / 1M

—

Codestral Embed

mistral/codestral-embed

Embedding

Code embedding model that can embed code databases and repositories to power coding assistants.

Context

—

In / 1M

$0.150

Out / 1M

—

Gemini Embedding 001

google/gemini-embedding-001

Embedding

State-of-the-art embedding model with excellent performance across English, multilingual and code tasks.

Context

—

In / 1M

$0.150

Out / 1M

—

Voyage AI's embedding model optimized for general-purpose and multilingual retrieval quality.

Context

—

In / 1M

$0.060

Out / 1M

—

Voyage AI's embedding model optimized for latency and cost.

Context

—

In / 1M

$0.020

Out / 1M

—

Embed v4.0

cohere/embed-v4.0

Embedding

A model that allows for text, images, or mixed content to be classified or turned into embeddings.

Context

128K

In / 1M

$0.120

Out / 1M

—

Voyage AI's embedding model with the best general-purpose and multilingual retrieval quality.

Context

—

In / 1M

$0.180

Out / 1M

—

Voyage AI's embedding model optimized for code retrieval.

Context

—

In / 1M

$0.180

Out / 1M

—

Text Embedding 005

google/text-embedding-005

Embedding

English-focused text embedding model optimized for code and English language tasks.

Context

—

In / 1M

$0.025

Out / 1M

—

Voyage AI's embedding model optimized for finance retrieval and RAG.

Context

—

In / 1M

$0.120

Out / 1M

—

Titan Text Embeddings V2

amazon/titan-embed-text-v2

Embedding

Amazon Titan Text Embeddings V2 is a light weight, efficient multilingual embedding model supporting 1024, 512, and 256 dimensions.

Context

—

In / 1M

$0.020

Out / 1M

—

Voyage AI's embedding model optimized for legal retrieval and RAG.

Context

—

In / 1M

$0.120

Out / 1M

—

Text Multilingual Embedding 002

google/text-multilingual-embedding-002

Embedding

Multilingual text embedding model optimized for cross-lingual tasks across many languages.

Context

—

In / 1M

$0.025

Out / 1M

—

text-embedding-3-large

openai/text-embedding-3-large

Embedding

OpenAI's most capable embedding model for both english and non-english tasks.

Context

—

In / 1M

$0.130

Out / 1M

—