frontier

Cohere

Command R+, best-in-class embeddings and rerankers.

live

Uptime (30d)

99.85%

Median tps

105

Median TTFT

290 ms

Price index

0.9×

vs. market median

Overview

HQ: Toronto, CA
Founded: 2019
Models: 7
Modalities: text
Regions: us-east, eu-west, canada

Strengths

ragembeddings

Route via llmcloud

curl https://api.llmcloud.ai/v1/chat/completions \
  -H "Authorization: Bearer $LLMCLOUD_KEY" \
  -H "X-Provider: cohere" \
  -d '{
    "model": "auto:quality",
    "messages": [{"role":"user","content":"hi"}]
  }'

Models served

command-a-03-2025

q 82.9130 tps$2.5/1M

command-r-plus-08-2024

q 79.1150 tps$2.5/1M

aya-expanse-32b

q 74.6200 tps$0.3/1M

command-r7b-12-2024

q 70.4320 tps$0.15/1M