Cohere

Enterprise AI with RAG and embeddings focus

RAGEmbeddingsEnterpriseMultilingualOpenAI-compatible
HQ: Toronto, CanadaFounded: 2019cohere.com

About Cohere

Cohere builds AI models optimized for enterprise use cases including retrieval-augmented generation (RAG), semantic search, and text classification. Their Command model family is designed for production deployments with strong multilingual support.

Key Models

Command ACommand R+Embed v3

Live Performance Data

Intelligence Score
48.0
Total Requests
0
Success Rate
0.0%
Avg Latency
400ms
Models
29
Tokens Processed
0

Cohere Models on Antbase

ModelScoreRequestsSuccess RateAvg Latencyp95 LatencyCapabilities
Rerank v3.580.000.0%400ms1000ms
Embed Multilingual v3.075.000.0%400ms1000ms
Rerank Multilingual v3.075.000.0%400ms1000ms
Rerank English v3.075.000.0%400ms1000ms
Embed English v3.075.000.0%400ms1000ms
Embed Multilingual Light v3.060.000.0%400ms1000ms
Embed English Light v3.060.000.0%400ms1000ms
Tiny Aya Water50.000.0%400ms1000ms
C4ai Aya Expanse 8b50.000.0%400ms1000ms
Command A Vision 07 202550.000.0%400ms1000ms
👁🔧
C4ai Aya Vision 8b50.000.0%400ms1000ms
👁
C4ai Aya Expanse 32b50.000.0%400ms1000ms
Command R7b Arabic 02 202550.000.0%400ms1000ms
🔧
Command A Translate 08 202550.000.0%400ms1000ms
🔧
Tiny Aya Earth50.000.0%400ms1000ms
Tiny Aya Fire50.000.0%400ms1000ms
Command A Reasoning 08 202550.000.0%400ms1000ms
🧠🔧
Tiny Aya Global50.000.0%400ms1000ms
C4ai Aya Vision 32b50.000.0%400ms1000ms
👁
Embed Multilingual V3.0 Image30.000.0%400ms1000ms
Rerank V4.0 Fast30.000.0%400ms1000ms
Embed Multilingual Light V3.0 Image30.000.0%400ms1000ms
Embed English V2.030.000.0%400ms1000ms
Embed Multilingual V2.030.000.0%400ms1000ms
Embed English Light V3.0 Image30.000.0%400ms1000ms
Embed English V3.0 Image30.000.0%400ms1000ms
Rerank V4.0 Pro30.000.0%400ms1000ms
Embed English Light V2.030.000.0%400ms1000ms
Embed V4.030.000.0%400ms1000ms

How to Use Cohere on Antbase

All Cohere models are available through Antbase's unified OpenAI-compatible API. You can either route directly to a specific Cohere model or let ANT's intelligent router automatically select the best model for your task.

python
from openai import OpenAI

client = OpenAI(
    base_url="https://antbase.ai/v1",
    api_key="your-ant-api-key",
)

# Let ANT auto-route (may use Cohere if optimal)
response = client.chat.completions.create(
    model="ant:auto",
    messages=[{"role": "user", "content": "Hello!"}],
)

# Or route directly to a Cohere model
response = client.chat.completions.create(
    model="cohere/command-a",
    messages=[{"role": "user", "content": "Hello!"}],
)

Why Use Cohere Through Antbase?

  • •No separate account needed — access Cohere models instantly through your Antbase API key.
  • •Intelligent routing — ANT automatically selects the best Cohere model for each task, or falls over to another provider if Cohere is slow or down.
  • •Same token prices — Antbase charges zero markup on Cohere token prices. You pay exactly what Cohere charges.
  • •Automatic failover — if Cohere has an outage, your requests seamlessly route to an equivalent model on another provider.