- Source
- Model registry API
- Verified
- 19 Sep 2026
- Confidence
- High
01What this is
- Author
- Cohere
- Family
- Command A
- Task
- text-generation
- Hugging Face
- CohereLabs/c4ai-command-a-03-2025
- OpenRouter
- cohere/command-a
- Also known as
- Command A, command-a, c4ai-command-a
02Registry facts
- LicenceFACT
cc-by-nc-4.0
- FreshRetrieved 19 Sep 2026
- ParametersFACT
111.1B
- FreshRetrieved 19 Sep 2026
- Context lengthFACT
not returned by the registry
- Evidence not verified
- Downloads (30 days)FACT
2,559
- FreshRetrieved 19 Sep 2026
- LikesFACT
395
- FreshRetrieved 19 Sep 2026
- GatedFACT
yes
- FreshRetrieved 19 Sep 2026
Model
- downloadsFACT
2559
- Verification may be outdatedRetrieved 19 Sep 2026
- gatedFACT
true
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · CohereFACT
256000
- Verification may be outdatedRetrieved 19 Sep 2026
- likesFACT
395
- Verification may be outdatedRetrieved 19 Sep 2026
- model licenseFACT
cc-by-nc-4.0
- Verification may be outdatedRetrieved 19 Sep 2026
- parameter countFACT
111057580032
- Verification may be outdatedRetrieved 19 Sep 2026
Pricing
- hosted price completion per m · CohereFACT
10.0000
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · CohereFACT
2.5000
- AgeingRetrieved 19 Sep 2026
Other
- available on platform · vendorFACT
vendor
- AgeingRetrieved 19 Sep 2026
- available on platform · azureFACT
azure
Evidence not verified — the quoted phrase was not found in the fetched document.
- Evidence not verified
- last modifiedFACT
2025-10-30T06:37:15.000Z
- Verification may be outdatedRetrieved 19 Sep 2026
- libraryFACT
transformers
- AgeingRetrieved 19 Sep 2026
03VRAM by quantisation
Peak VRAM for serving this model, computed by lib/deployment/hardware.ts from weights + KV cache + 15% runtime overhead. Inputs: 111.1B parameters, 8,192 tokens of context (assumed — none fetched yet), 4 concurrent requests (assumed).
| Quantisation | Weights | Total |
|---|---|---|
| bf16bf16 is two bytes per weight, the same arithmetic as fp16. | 222.12 GB | 272.72 GB |
| int8 | 111.06 GB | 145 GB |
| int4 | 55.53 GB | 81.15 GB |
What this estimate assumes
- Weights: 111.1B parameters × 2 bytes per parameter (fp16) = 222.12 GB.
- No model configuration was supplied, so the KV cache uses the size heuristic for this band: 0.459 MB per token, from extrapolated above 90B — no configuration was fetched for this band.
- KV cache: 0.459 MB per token × 8,192 tokens of context × 4 concurrent requests = 15.03 GB, sized for every user holding a full context at once.
- Overhead: 15% of weights plus KV cache for the runtime, activations and memory fragmentation = 35.57 GB.
- GB means 10⁹ bytes, matching how GPU memory is advertised.
- KV cache held at fp16 (2 bytes per element); quantising weights does not by itself quantise the cache.
- Peak figure, not average: prefix caching and paged attention usually keep real usage lower, while speculative decoding, CUDA graphs and a second resident model push it higher.
- "Concurrent" counts requests generated at the same instant, not people: 4 simultaneous requests is the worst case this estimate is built on — measure yours before buying.
04Hardware profiles
No hardware profile was sized for this answer.
05Hosted providers
- Prompt (per million tokens, USD)FACT
2.5
Source: openrouter
- FreshRetrieved 19 Sep 2026
- Completion (per million tokens, USD)FACT
10
- FreshRetrieved 19 Sep 2026
| Provider | Context |
|---|---|
| Cohere | 256,000 |
06Deployment stacks
No published deployment stack names this model yet.
07Evidence
- 01Tier 2official vendor legal documentationVendor legal and technical documentation
An Overview of Cohere's Models
https://docs.cohere.com/docs/models.md
AgeingRetrieved 19 Sep 2026sha256:0de8c37c285c1 record
- 02–04Tier 4official repository / model cardOpenRouter
OpenRouter endpoints — cohere/command-a
https://openrouter.ai/api/v1/models/cohere/command-a/endpoints
Verification may be outdatedRetrieved 19 Sep 2026sha256:52afeb4fe9093 records · ·
- 05–11Tier 4official repository / model cardHugging Face Hub
Hugging Face model card data — CohereLabs/c4ai-command-a-03-2025
https://huggingface.co/api/models/CohereLabs/c4ai-command-a-03-2025
Verification may be outdatedRetrieved 19 Sep 2026sha256:699870afc5e17 records · · · · · ·
Improve this page
Sign in to contribute
From the field
0 deployments · 0 questions
Nobody has reported deploying this here yet, and no question has been opened against this page. Both appear once a reviewer accepts them.