Command A with Jev
Command A is a model from Cohere, released 2025-03-13. It costs $2.50 per million input tokens and $10 per million output tokens, reads up to 256K tokens of context, and writes up to 8,192 tokens in one reply. Through llm11, set model to cohere/command-a.
- Input price
- $2.50 / 1M
- Output price
- $10 / 1M
- Context window
- 256K tokens
- Max output
- 8K tokens
- Released
- 2025-03-13
- Accepts
- text
- Intelligence index
- 13.1
Artificial Analysis, via the catalogue
Read from the live catalogue and refreshed daily. At blended list price, 14% of the 332 priced models we can call cost more.
Using Command A with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Command A does the answering when Jev sends it work, or when you name it yourself. Command A falls in the llm11-balanced band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool.
Jev is new, so we have not published results for Command A with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00325 | $3.25 |
| Question over retrieved documents | 4,000 / 500 | $0.015 | $15.00 |
| Long document summary | 30,000 / 1,000 | $0.085 | $85.00 |
Cheaper models to try
Nearest in price and below Command A, each within a few points of it on the intelligence index.
| Model | Input / 1M | Output / 1M | Context | Index | Released |
|---|---|---|---|---|---|
| Anthropic Claude Sonnet 5.5 | $2.00 | $10 | 1M | 56 | |
| OpenAI GPT-6 Sol | $2.00 | $10 | 1.05M | 47.5 | |
| OpenAI GPT-5.6 Sol | $2.00 | $10 | 1.05M | 47 | |
| Anthropic Claude Sonnet 5 | $2.00 | $10 | 1M | 38.2 |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="cohere/command-a",
messages=[{"role": "user", "content": "Hello"}],
)More from Cohere
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Command A+ | $0.300 | $1.50 | 192K | |
| Command R7B (12-2024) | $0.037 | $0.150 | 128K | |
| Command R (08-2024) | $0.150 | $0.600 | 128K | |
| Command R+ (08-2024) | $2.50 | $10 | 128K |
Questions
- What is Command A with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Command A does the answering when Jev sends it work, or when you name it yourself. Command A falls in the llm11-balanced band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is Command A a System One model?
- No. Command A answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does Command A cost?
- $2.50 per million input tokens and $10 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.015, so a thousand of them is about $15.00. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Command A context window?
- 256,000 tokens, with up to 8,192 tokens in a single reply.
- Does Command A support tool calling and structured output?
- The catalogue lists structured output, but it does not list tool calling and reasoning controls.
- Can I use Command A through llm11?
- Yes. Set model to cohere/command-a on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Command A?
- Routing decisions are made by Jev, TypeSafe AI's System One model. Command A falls in the llm11-balanced band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool.
- What is a cheaper alternative to Command A?
- Nearest in price and below it: Anthropic Claude Sonnet 5.5 at $2.00 in and $10 out, OpenAI GPT-6 Sol at $2.00 in and $10 out and OpenAI GPT-5.6 Sol at $2.00 in and $10 out. Nearest in price and below Command A, each within a few points of it on the intelligence index.