Generate API
AI / MLCohere
Enterprise-focused text generation, embeddings, reranking, and RAG-optimized models
Reported Latency
Typical performance from public reports -- not live measurements
Average: 700ms
p50
480ms
p95
1,800ms
p99
3,500ms
Reliability
99.8%observed uptime
Pricing
Free tier
1,000 requests/month
Paid starts at
$1.00 / 1M input tokens (Command-R)
Technical Details
Authentication
API Key
Rate limit
100 RPM (trial)
Protocols
REST
SDKs
PythonNode.jsJavaGo
Regions
USEU
Last updated: 2026-04-12