Cohere
100.00%Context256K
Max output8K
p50 latency241 ms
Throughput72.5 t/s
Input price$2.5
Output price$10
No training
Model directory
Baseer model profileLanguage model
cohere/command-a
Command A
Command A is Cohere's most performant model to date, excelling at tool use, agents, retrieval augmented generation (RAG), and multilingual use cases. Command A has a context length of 256K, only requires two GPUs to run, and has 150% higher throughput compared to Command R+ 08-2024.
Input / 1M tokens$2.5
Output / 1M tokens$10
Maximum context256K
Inference providers1
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Cohere | 256K | 8K | 241 ms | 72.5 t/s | 100.000% | $2.5 | $10 |
What can this model do?
Available modalities and capabilities across inference providers.
TextTool useTools
Technical profile
- Model type
- Language model
- Release date
- Mar 13, 2025
- Knowledge cutoff
- 2024-10
- Regions
- —
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
cohere/command-aModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.