Command A Reasoning pricing, context window and limits
Command A Reasoning costs $2.5 per million input tokens and $10 per million output tokens at Cohere list price. It accepts up to 256,000 tokens of context and returns up to 32,000 tokens.
- Model id
command-a-reasoning-08-2025 - Snapshot
What does Command A Reasoning cost?
| Input | $2.5 |
|---|---|
| Output | $10 |
| Cached input (read) | — |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can Command A Reasoning read and write?
| Context window | 256,000 |
|---|---|
| Max output | 32,000 |
What can Command A Reasoning do?
| Vision (image input) | No |
|---|---|
| Tool calling | Yes |
| Structured output | No |
| Reasoning | Yes |
| Input | text |
| Output | text |
What does a request to Command A Reasoning cost?
| A typical request: 1,000 tokens in, 500 out | $0.0075 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.035 |
| 1,000 typical requests | $7.5 |
| 1 million tokens in and 1 million out | $12.5 |
Among 11 Cohere models with a published price, Command A Reasoning is the 6th cheapest by input price. Its context window is the largest of 17. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Command A Reasoning through DVARA?
Configure the cohere provider in the DVARA LLM Gateway and send the model id command-a-reasoning-08-2025. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other Cohere models are there?
- Command A Plus$2.5 in · $10 out · 128K context
- Command A Translate$2.5 in · $10 out · 8K context
- Command A$2.5 in · $10 out · 256K context
- Command A Vision$2.5 in · $10 out · 128K context
- Command R$0.15 in · $0.6 out · 128K context
- Command R+$2.5 in · $10 out · 128K context
- Command R7B$0.0375 in · $0.15 out · 128K context
- Command R7B Arabic$0.0375 in · $0.15 out · 128K context
- Aya Vision 32B— in · — out · 16K context
- Aya Expanse 32B— in · — out · 128K context
- North Mini Code$0 in · $0 out · 256K context
- North Small Translate$0 in · $0 out · 33K context
Which models from other providers are similar to Command A Reasoning?
These are the closest in context window and input price, one per provider.
- Magistral Medium (latest)Mistral AI · $2 in · $5 out · 262K context
- Kimi K2.7 Code HighSpeedMoonshot AI · $1.9 in · $8 out · 262K context
- Claude Sonnet 4.5 (latest)Anthropic · $3 in · $15 out · 200K context
- Claude Sonnet 4.5Amazon Bedrock · $3 in · $15 out · 200K context
- o3OpenAI · $2 in · $8 out · 200K context