Cohere: Embed English Light v3
stableEmbed English Light v3 is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.
embed-english-light-v3.0embed
Context
512
tokens
Max output
-
tokens
Input
$0.10
per 1M
Output
-
per 1M
Activity
Daily period usage
Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.
Providers
ProviderContextInput /MOutput /M
Pricing
| Item | Price | Unit |
|---|---|---|
| Input | $0.10 | per 1M tokens |
| Output | - | per 1M tokens |
Performance
Reliability
Compare
Compare usage and performance
Place this model beside up to three other catalog models.
Capabilities
Capabilities
Modalities
Input
Output
Details
- Model ID
- embed-english-light-v3.0
- Family
- embed
- Status
- stable
- Knowledge
- -
- Released
- -
Gateway Config
- API
- 2024-01-01
- Auth
- COHERE_API_KEY
- Discovery
- static
- Provider type
- static
Quick Start
index.ts
Endpoint
Base URL
https://api.cohere.comChat completions
https://api.cohere.com/chat/completionsModel
embed-english-light-v3.0Auth env
COHERE_API_KEYEmbed English Light v3 FAQ
How much does the Embed English Light v3 API cost?
Through Cohere, Embed English Light v3 costs $0.10 per 1M input tokens.
What is the context window of Embed English Light v3?
Embed English Light v3 accepts up to 512 tokens of context on Cohere.
What can Embed English Light v3 do?
Embed English Light v3 supports embeddings. It accepts text input.
How do I call Embed English Light v3 through Everstack?
Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @cohere/embed-english-light-v3.0. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.
