Command A vs Mistral Medium 3.5
Cohere against Mistral AI, costed on the same three workloads. Mistral Medium 3.5 is cheaper on all three workloads.
Run this comparison on your own numbers
Monthly bill, side by side
| Workload | Command A | Mistral Medium 3.5 | Difference |
|---|---|---|---|
| Support chatbot 2,500 six-turn conversations a day |
$9,056 | $6,041 | $3,015 (+50%) |
| Document summarizer 1,000 single-shot summaries a day |
$1,155 | $729 | $426 (1.6×) |
| Coding agent 200 twelve-turn sessions a day |
$6,570 | $4,212 | $2,358 (1.6×) |
No prompt caching and no batch discount on either side, so the comparison is like for like. Both figures assume 30 days a month.
The rate cards
| Command A | Mistral Medium 3.5 | |
|---|---|---|
| Input, per 1M tokens | $2.5 | $1.5 |
| Output, per 1M tokens | $10 | $7.5 |
| Cached input | not published | $0.15 |
| Context window | 256K | 262K |
| Maximum output | 8K | 262K |
| Reasoning model | no | no |
| Vision | no | yes |
Beyond the price
- Mistral Medium 3.5 reads up to 262K tokens of context in one request; Command A stops at 256K.
- Mistral Medium 3.5 can write up to 262K tokens in one response, against 8K for Command A.
- Only Mistral Medium 3.5 accepts images as input.
- Only Mistral Medium 3.5 publishes a cached-input rate, which cuts the cost of resending a long, unchanging prompt.
Run this comparison on your own numbers
Full detail: Command A pricing · Mistral Medium 3.5 pricing
More comparisons
Other head-to-heads that include Command A or Mistral Medium 3.5.
- Command A vs Nova 2 Pro
- Command A vs Claude Haiku 4.5
- Command A vs GPT-5.4 Mini
- Mistral Medium 3.5 vs Nova 2 Pro
- Mistral Medium 3.5 vs Claude Haiku 4.5
- Mistral Medium 3.5 vs o4-mini
Common questions
Which is cheaper, Command A or Mistral Medium 3.5?
Mistral Medium 3.5 is cheaper on all three workloads.
How much would Command A and Mistral Medium 3.5 cost each month?
On PromptSpend's standard workloads, per month: support chatbot: Command A $9,056, Mistral Medium 3.5 $6,041 (Mistral Medium 3.5 is cheaper by $3,015); document summarizer: Command A $1,155, Mistral Medium 3.5 $729 (Mistral Medium 3.5 is cheaper by $426); coding agent: Command A $6,570, Mistral Medium 3.5 $4,212 (Mistral Medium 3.5 is cheaper by $2,358). No prompt caching and no batch discount is assumed.
How do Command A and Mistral Medium 3.5 differ apart from price?
Mistral Medium 3.5 reads up to 262K tokens of context in one request; Command A stops at 256K. Mistral Medium 3.5 can write up to 262K tokens in one response, against 8K for Command A. Only Mistral Medium 3.5 accepts images as input. Only Mistral Medium 3.5 publishes a cached-input rate, which cuts the cost of resending a long, unchanging prompt.