Cohere · AI model
Command A
111B-parameter Command model released in March 2025 for tool use, agents, RAG and multilingual tasks in 23 languages; 256K context, 8K output; text-only; weights under a non-commercial CC-BY-NC 4.0 licence.
Last verified Available 5 sources
Key specs
- Provider
- Cohere
- Family
- Command A
- API identifier
- command-a-03-2025
- Availability
- Available
- Release date
- 2025-03-13
- License
- Open weights (CC-BY-NC 4.0 License with Acceptable Use Addendum)
- Context window
- 256,000 tokens
- Max output
- 8,000 tokens
- Knowledge cutoff
- June 2024
- API access
- Yes
- Consumer app
- No
Capabilities
Inputs
- Text input Yes
- Image input No Image Inputs marked as not supported in the capabilities panel on the model's docs page; docs model table lists modality as Text
- Audio input No Docs model table lists modality as Text only
- Video input No Docs model table lists modality as Text only
- File input Unknown
Outputs
- Text output Yes
- Image output No Docs model table lists modality as Text only
- Audio output No Docs model table lists modality as Text only
Features
- Reasoning None Reasoning marked as not supported in the capabilities panel on the model's docs page
- Tool calling Yes
- Web search Unknown
"Unknown" means we have not verified this capability yet; it does not mean the model lacks it.
Pricing
Estimate your monthly cost →| Dimension | Tier | Price | Since | Verified | Source |
|---|---|---|---|---|---|
| Input tokens | base | $2.50 per 1M tokens | 2026-10-12 | 2026-10-25 | Command A | Cohere Listed on the Command A docs page; Command A is not shown on cohere.com/pricing |
| Output tokens | base | $10.00 per 1M tokens | 2026-10-12 | 2026-10-25 | Command A | Cohere Listed on the Command A docs page; Command A is not shown on cohere.com/pricing |
Prices are shown in the currency the provider publishes; we never convert currencies.
Benchmarks
| Benchmark | Setting | Score | Reported by | Measured | Verified | Source |
|---|---|---|---|---|---|---|
| Text Arena Arena score, higher is better | Overall; style control on (default view); no effort suffix (row 'command-a-03-2025') | 1,354 | Third party | 2026-10-23 | 2026-10-25 | Text Arena leaderboard (Arena) |
Scores measure voter preference, which can be influenced by answer style and length. The leaderboard offers a style-control adjustment, so record which view was used. Scores shift with every update, so a value is only meaningful together with its leaderboard date. Entries marked "Preliminary" or with few votes have wide confidence intervals. The same model can appear several times with different reasoning-effort suffixes (for example -high or -max). Category views (Coding, Math, Creative Writing and others) are different rankings from Overall.
One row per result, without rank numbers: each result was measured under its own setting (effort level, harness, tools, test version), as stated by the source, and scores compare only within the same setting. Self-reported results come from the provider and have not been reproduced independently.
Rankings
- #39 of 42 in Best AI API as of 2026-10-26
Derived from our published ranking snapshots; each ranking explains its criteria and weights.
Compare Command A
Guides
About Command A
Command A is a 111B-parameter model released on March 13, 2025, aimed at tool use, agents, retrieval-augmented generation and multilingual use in 23 languages. It has a 256,000-token context window and up to 8,000 output tokens, and according to Cohere runs on two A100 or H100 GPUs. Its docs page lists API pricing of $2.50 per 1M input tokens and $10.00 per 1M output tokens, although the model is not shown on cohere.com/pricing. Weights are published on Hugging Face under a non-commercial CC-BY-NC 4.0 licence with Cohere Labs' acceptable use terms.
Strengths and weaknesses
Strengths
- 256,000-token context window
- Documented for tool use, multi-step agents and RAG with citations
- Trained for 23 languages
- Runs on two A100 or H100 GPUs (per Cohere docs)
Weaknesses
- Text-only input
- Maximum output of 8,000 tokens
- No reasoning mode (per its docs page)
Sources
Last verified Page updated 2026-10-26