cohere logo
cohere

Cohere: Embed 5 Fast

Source description (English)

Embed 5 Fast is the lower-latency, cost-efficient tier of Cohere's Embed 5 family of multimodal embedding models (about 1B parameters). It embeds text, images, and interleaved text and image content...

Overview

Model specifications

Context
128,000 tokens
Maximum output
115,200 tokens
Architecture
text+image->embeddings
Tokenizer
Cohere
Knowledge cutoff
Not provided
Moderated
Yes
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.08
per 1M tokens
Image input
$0.4
/M image tokens
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/embeddings \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"cohere/embed-5-fast","input":"Your text here"}'
Capabilities

Input → Output

Input
textimage
Output
embeddings
API

Supported API parameters

Available providers

1 Provider

Checked: November 4, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Cohere

Not provided
Context
128K
Maximum output
115K
Input
$0.08
Output
Free
Cache read
Not provided
Cache write
Not provided
cohere

4 models

All models