Cohere
Available in Shortly AI
Command A
Released March 13, 2025
Tool Use
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.
- Context window
- 256K tokens
- Maximum output
- 8K tokens
- Input pricing
- $2.50/M
- Output pricing
- $10.00/M
Independent benchmark
LiveBench historical snapshot
44.1overall
Historical benchmark data from LiveBench, release 2025-05-30. Scores are pinned and are not fetched on page load.
36.3
55.3
3.3
45.5
48.5
36.7
82.9
| Category | Score |
|---|---|
| Reasoning | 36.333 |
| Coding | 55.343 |
| Agentic Coding | 3.333 |
| Mathematics | 45.542 |
| Data Analysis | 48.457 |
| Language | 36.696 |
| Instruction Following | 82.904 |
Benchmarks measure selected evaluation tasks and do not guarantee performance for every prompt or workflow.
FAQ
Similar AI models
Muse Spark 1.3MetaMuse Spark 1.3 is Meta’s multimodal reasoning model for long-horizon agentic and coding workflows. With a 1M-token context window, reliable tool calling, higher first-attempt accuracy, and native understanding of video, images, and documents, it helps developers build capable coding agents and AI development workflows with fewer unnecessary turns and cleaner output.GLM 5.3Z.aiGLM 5.3 delivers comprehensive advancements in complex software engineering and agent capabilities. It uses the same base model as GLM-5.2, with all improvements driven by post-training.Muse Spark 1.2MetaA coding-optimized model purpose-built for agentic workflows. Improvements to code generation, debugging, and codebase understanding — with a 1M context window that handles your entire project in one session.
Available with one subscription
Start with Command A in Shortly AI
Keep your conversations, files and model choices together in one workspace.