Command A
CohereReleased Mar 13, 2025Open weights · CC-BY-NC 4.0command-a
- Knowledge cutoff
- January 2025
- Context
- 256k tokens
- Max output
- 8k tokens
- Cohere's API
- yes
Read Sep 3, 00:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Cohere · cutoff: docs.cohere.com
Its only host, Cohere, serves a weights precision we can't read (host terms). Weights and context per host
Run it yourself
open weights, CC-BY-NC 4.0 · fits 4 of the 6 workstations in our guideSelf-host guide ›- Parameters
- 111B
- dense
- Memory needed
- 67 GB
- in INT4 · 133 GB in INT8
- Smallest cloud setup
- A100
- 80 GB · $1.19/h, about $869 a month
- Worth it above
- 69M tokens
- a month, against the cheapest API at $12.50 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 67 GB | A100 · $1.19/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 133 GB | 2× H100 · $4.30/h | near-lossless |
| FP16 (full) | 266 GB | 4× H100 · $8.60/h | reference quality |
At home: in INT4 it fits a Mac Studio M5 Ultra (96 GB unified), about $5,499 once, or $0.2092/h over 3 years, electricity aside; it pays for itself after about 440M tokens against the cheapest API.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | Checked |
|---|---|---|---|---|
| Cohereprecision not read: host terms · 250K ctx · 8K out | $2.50 | $10.00 | — | Sep 3 |
1 provider · prices per million tokens, read Sep 3, 00:00 UTC · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| Cohere | not read: host terms | 250K | 8K | — | — | — |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
Command A spec sheet, field by field, with sources
Command A spec sheetmaker-declared
What the maker declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- to verify
- Parameters
- to verify
- Active experts
- to verify
- Weight precision
- to verify
- License
- CC-BY-NC 4.0 — open weights, conditionalScope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- January 2025maker's docs
- Modalities
- to verify
- Max output (official)
- to verify
- Release date
- to verify≈ March 13, 2025 third-party catalogue — not the maker's figure
- Maker lifecycle status
- to verify
huggingface.co · maker's documentation · read 2026-09-07 · 2 of 10 fields published by the maker
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| Cohere | $7.50 | $25.00 | $20.00 |
What each host bills for 1,000 requests of a representative job
Your own workload
Other Cohere models · all its models, hosts and history ›
- Command A+1 provider · from $1.80
- Command R1 provider · from $0.75
- Command R+ (08-2024)1 provider · from $12.50
- Command R7B (12-2024)1 provider · from $0.19
- North Mini Code0 provider · from —