Command A
Cohere · released Mar 11, 2025 · CohereForAI/c4ai-command-a-03-2025
- Type
- Open weightsCreative Commons Attribution-NonCommercial 4.0
- Params
- 111B
- Context
- 256K
about 192K words of context · download allowed, licence restricts use
Our take
Written Sep 3, 2026Command A is a 111.1-billion-parameter text-only model from Cohere with a 256,000-token request limit. Its weights can be downloaded, but the licence restricts use to non-commercial projects.
Pick this for long-context text tasks at 256,000 tokens where downloadable weights matter more than commercial freedom. Use it through Cohere directly if 51 tokens per second is acceptable and you want direct billing. Skip it if you need commercial deployment, fine-tuning for profit, or any measured quality scores to guide your choice.
The case for it
- 111.1 billion parameters — one of the larger openly downloadable models we list.
- 256,000-token request limit, unusually long for the downloadable tier.
- Identical pricing across both tracked providers, so provider choice comes down to routing and throughput rather than cost.
The case against it
- Non-commercial licence only: no commercial products, no profit-making fine-tuning, no redistribution for business use.
- No benchmark scores in our data — chat, reasoning, coding and general knowledge all unverified.
- No disclosed active-parameter figure, so the efficiency of the 111.1 billion cannot be assessed.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M1 Ultra (64-core GPU) · 128 GB
Room to spare. 22.3 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked between 5 days and 9 days ago — each listing carries its own date.
- per 1M tokens
- $2.50 in / $10.00 out
- Context served
- 256K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $2.50 / $10.00checked 5 days ago | 256K | not measured | Unknown | Unknown | Unknown |
| CohereThrough OpenRouter | $2.50 / $10.00checked 9 days ago | 256K8K max reply | not measured | No | Yes30 days | Confirmed |
OpenRouterAcross the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✗ | ✓ | ✓ |
| CohereThrough OpenRouter | ✗ | ✓ | ✓ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsCreative Commons Attribution-NonCommercial 4.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Creative Commons Attribution-NonCommercial 4.0
Weights are downloadable but commercial use is prohibited. Research and personal use only.
Identifiers
- Hugging Face
- CohereForAI/c4ai-command-a-03-2025
- Takes in, gives back
- Text in, text out
- Catalogue slug
- cohere-command-a