Command A
Command A is a text-based AI model by Cohere. It features a 256K token context window, 54 tok/s output speed, $2.50/1M input tokens pricing. It scores 13.5 on the intelligence index.
Strengths
- +Large context window (256K)
Benchmarks
Intelligence13.5Coding9.9Math13.0
MMLU-Pro
0.7
GPQA
0.5
LiveCodeBench
0.3
Intelligence
13.5
Coding
9.9
Math
13.0
Output Speed
54 tok/s
Latency (TTFT)
0.58s
Blended Price
$4.38/M
Pricing per 1M Tokens
| Input (Prompt) | $2.50 |
| Output (Completion) | $10 |
| Cache Read | Free |
| Cache Write | Free |
Specifications
| Context Length | 256K |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Compare Command A with:
Alternatives to Command A
More from Cohere
Frequently Asked Questions
How much does Command A cost?
Command A costs $2.50/1M input tokens and $10/1M output tokens.
What is Command A's context window?
Command A supports a context window of 256K tokens, which is approximately 128 pages of text.
Is Command A good for coding?
Command A has a lower coding score of 9.9. For demanding coding tasks, consider a model with a higher coding benchmark.
How fast is Command A?
Command A generates output at 54 tok/s. Time to first token is 0.58s.
Is there a free version of Command A?
Last updated: