Command A
Cohere command model for multilingual enterprise agents, tools, and chat
Cheapest input
$2.50
$/MTok · models.dev
Cheapest output
$10
$/MTok
Context
256K
tokens
Offers
6
3 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestcohere/command-a | Kilo Gateway | $2.50 | $10 | $0 | 256K |
| OpenRoutercohere/command-a | OpenRouter | $2.50 | $10 | $0 | 256K |
| models.devcohere/command-a | Vercel AI Gateway | $2.50 | $10 | $0 | 256K |
| LiteLLMcohere/command-a | — | $2.50 | $10 | $0.25 | — |
| LiteLLMcommand-a | — | $2.50 | $10 | $0.25 | — |
| LiteLLMvercel_ai_gateway/cohere/command-a | — | $2.50 | $10 | $0.25 | — |
Capabilities
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Knowledge cutoff: 2024-08-31Released: 2025-03-13Family: command-a
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence22.5
- AA coding27.8
- AA agentic9.2
Sources: Arena AI, Artificial Analysis. See /benchmarks.