Cohere · LLMs & Coding
Command A
Catalog data · checked Nov 16, 2026
Command A is a language model from Cohere, released in March 2025. It reads text and writes text, with a context window of 256K tokens and up to 8K output tokens per answer. It costs $2.5 per million input tokens and $10 per million output tokens. That puts it in the upper price range: 82% of the 185 paid language models we track cost less.
What it can do
- Tool calling
- Structured output
- Reasoning mode
- Image input
- File input
- Audio input
- Video input
- Image output
- Audio output
- Prompt caching
What it costs in practice
| 1,000 support replies1,000 chats with 800 input and 250 output tokens each | $4.5 |
| Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens out | $0.395 |
| 10,000 product descriptions300 input and 200 output tokens per text | $27.5 |
| One day of agentic codingabout 3M input and 150K output tokens across many calls | $9 |
Calculated from the list prices above. Your bill depends on your real token counts. Use your own numbers →
Compare Command A with
Questions & answers
How much does Command A cost?
Command A costs $2.5 per 1 million input tokens and $10 per 1 million output tokens (USD, list price checked Nov 16, 2026).
How large is the context window of Command A?
Command A can process up to 256,000 tokens per request and return up to 8,000 tokens. As a rule of thumb, 1,000 tokens are about 750 English words.
Does Command A support tool calling?
Yes. The API accepts tool (function) definitions and also supports structured JSON output.
Can Command A read images?
No, this model accepts text only.
