Command R+ vs GPT-4o Mini: Detailed Comparison
Choosing between Command R+ (Cohere) and
GPT-4o Mini (OpenAI) comes down to three things:
per-token pricing, context window, and which capability matters most for your workload.
Command R+ costs $2.50/M input vs
$0.15/M for GPT-4o Mini;
context windows are 128K vs
128K tokens. Detailed breakdown below.
Side-by-side specs
| Spec | Command R+ | GPT-4o Mini |
|---|
| Provider | Cohere | OpenAI |
|---|
| Released | 2024-04-04 | 2024-07-18 |
|---|
| Input price |
$2.50/M |
$0.15/M |
| Output price |
$10.00/M |
$0.60/M |
| Cached input |
— |
$0.0750/M |
| Context window |
128K |
128K |
| Max output |
4K |
16K |
| Modalities |
text |
text image |
| Tokenizer |
cohere |
o200k_base |
Capability matrix
| Capability | Command R+ | GPT-4o Mini |
|---|
| function calling |
Yes |
Yes |
| json mode |
Yes |
Yes |
| streaming |
Yes |
Yes |
| rag |
Yes |
No |
| citations |
Yes |
No |
| vision |
No |
Yes |
Per-call cost on typical workloads
| Workload (in/out tokens) | Command R+ | GPT-4o Mini | Cheaper by |
|---|
| Standard chat (1K / 500) |
$0.007500 |
$0.000450 |
GPT-4o Mini by $0.007050 |
| RAG (4K / 500) |
$0.015000 |
$0.000900 |
GPT-4o Mini by $0.014100 |
| Long doc (20K / 1K) |
$0.060000 |
$0.003600 |
GPT-4o Mini by $0.056400 |
| Very long context (100K / 2K) |
$0.265000 |
$0.015900 |
GPT-4o Mini by $0.249100 |
When to choose Command R+ over GPT-4o Mini
- Supports rag — GPT-4o Mini does not.
- Supports citations — GPT-4o Mini does not.
When to choose GPT-4o Mini over Command R+
- Per-token input cost is 94% lower than Command R+.
- Supports vision — Command R+ does not.
Related comparisons