Cohere
Command A
Released Mar 13, 2025 · 22B tokens this week · 3 providers
Overview
Cohere's enterprise flagship, tuned for retrieval-augmented generation with inline citations. Covers 23 languages and is designed to run on relatively little hardware for its class. A natural fit for regulated document workflows.
Providers
Reference data — not yet measured from live traffic
| PROVIDER | MAX OUT | OUTPUT /M | QUANT | |||||
|---|---|---|---|---|---|---|---|---|
CohereCheapest | 262K | 8K | $2.50 | $10.00 | 620ms | 88 | 99.70% | Full |
Amazon Bedrock | 262K | 8K | $2.75 | $11.00 | 720ms | 74 | 99.75% | Full |
Azure AI Foundry | 131K | 8K | $2.80 | $11.20 | 740ms | 70 | 99.65% | Full |
Latency p50 reflects a provider’s API endpoint responsiveness — the round-trip to its API, not per-token inference time. These figures, with throughput and uptime, are reference data until the gateway aggregates its own traffic.
Price comparison
Blended $ per 1M tokens
Blended rate per 1M tokens, weighted one part prompt to three parts completion — roughly the shape of a chat workload. Your mix will move the number.
Call it
OpenAI-compatible — swap the base URL and go
curl https://model.cards/api/v1/chat/completions \
-H "Authorization: Bearer $MODELCARDS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "cohere/command-a",
"messages": [
{ "role": "user", "content": "Summarize the tradeoffs of speculative decoding." }
]
}'