Co
Cohere: Command A 03-2025
Free allowance
Up to1,000requests / month
via Cohere
- 20 requests / minute
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
- text
- Output
- text
Providers
Available through 2 free providers. Use the model ID and API settings below to connect.
Vercel AI Gateway
VAVercel AI Gateway
* The provider match may differ from this model. Check its docs for details.
Benchmarks
Compare scores and explore results by category.
No benchmark results are available for this model yet.
Frequently asked questions
Free access, setup, and what to expect.
Command A 03-2025 is available with up to 1,000 requests / month free through Cohere. Additional limits apply at the same time: 20 requests / minute. Free allowances can change. Check the Command A 03-2025 provider limits before you start.
To use Command A 03-2025, choose one of the listed Command A 03-2025 API providers and follow the provider’s account and API-key setup guide. Copy the Command A 03-2025 model ID and connection settings for your chosen provider into your app or API client. Model IDs can differ between providers. API requests go directly to the provider; Free Models is a comparison site.
Command A 03-2025 accepts text as listed input formats. Listed output formats include text. Image or audio input support does not imply image or audio generation. Check the chosen provider’s Command A 03-2025 documentation for supported file types and request formats.
Command A 03-2025 has a listed context window of 256K tokens. Tokens are small pieces of content rather than a word count. Instructions, conversation history, and other inputs use context space, and the response also needs room. The maximum output length for Command A 03-2025 may be smaller than the context window and can vary by provider.
Command A 03-2025 has tool calling support listed; reasoning support isn’t listed. Reasoning enables additional processing for complex problems. Tool calling allows a model to request functions that your app executes. Check the chosen provider’s documentation for capability availability and setup.
No benchmark results are listed for Command A 03-2025 yet. Missing scores don’t establish poor performance. Compare scores within the same benchmark: coding indexes, Elo ratings, and win rates measure different things. The index comparison charts include only scored free models listed on Free Models. Evaluate Command A 03-2025 on examples from your own task alongside context size and provider limits.