Very long inputs
Choose Command A
Command A reads up to 256k tokens per request, against 128k for GPT-4o Mini Search Preview.
Command A vs GPT-4o Mini Search Preview: price, context and capabilities
Choose Command A for very long inputs. Choose GPT-4o Mini Search Preview for images as input.
In short
- A price comparison is not possible: one of them has no comparable published price.
- Command A reads more per request: 256k tokens against 128k.
- Only GPT-4o Mini Search Preview offers vision, batch api.
Which should you choose?
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Images as input
Choose GPT-4o Mini Search Preview
GPT-4o Mini Search Preview accepts images as input; Command A does not.
Specifications side by side
| Command A | GPT-4o Mini Search Preview | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Category | Language models | Language models |
| Status | Generally available | Deprecated |
| Headline price | No data | No data |
| Input | No data | No data |
| Output | No data | No data |
| Cached input | No data | No data |
| Context window | 256k | 128k |
| Max output | No data | 16k |
| Released | March 2025 | Mar 11, 2025 |
| Knowledge cutoff | No data | October 2023 |
| Licence | Proprietary | Proprietary |
| Capabilities | Tool calling, Structured output | Vision, Tool calling, Structured output, Batch API |
| API model id | command-a-03-2025 | gpt-4o-mini-search-preview |
Benchmarks side by side
Leader in bold.
| Benchmark | Command A | GPT-4o Mini Search Preview |
|---|---|---|
| Terminal-Bench Hard | 0.8% | No data |
| GPQA Diamond | 52.7% | No data |
| Humanity's Last Exam | 4% | No data |
| IFBench (instruction following) | 36.5% | No data |
| τ²-Bench (agentic tool use) | 15.2% | No data |
| Long-context reasoning (AA-LCR) | 21.3% | No data |
Independent evaluations by Artificial Analysis, run the same way for every model, at the reasoning setting shown. Percentages unless marked as an index.
Frequently asked questions
Should I choose Command A or GPT-4o Mini Search Preview?
Choose Command A for very long inputs. Choose GPT-4o Mini Search Preview for images as input.
Which is cheaper, Command A or GPT-4o Mini Search Preview?
A price comparison is not possible: one of them has no comparable published price.
Which has the larger context window, Command A or GPT-4o Mini Search Preview?
Command A reads more per request: 256k tokens against 128k.
What is the difference between Command A and GPT-4o Mini Search Preview?
Command A is made by Cohere and GPT-4o Mini Search Preview by OpenAI. A price comparison is not possible: one of them has no comparable published price. Command A reads more per request: 256k tokens against 128k. Only GPT-4o Mini Search Preview offers vision, batch api.