Very long inputs
Choose Command A
Command A reads up to 256k tokens per request, against 200k for codex-mini-latest.
codex-mini-latest vs Command A: price, context and capabilities
Choose codex-mini-latest for images as input and the latest release. Choose Command A for very long inputs.
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 200k.
- codex-mini-latest is the newer model (May 15, 2025, against March 2025).
- Only codex-mini-latest offers vision, reasoning, batch api.
Which should you choose?
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Images as input
Choose codex-mini-latest
codex-mini-latest accepts images as input; Command A does not.
Latest release
Choose codex-mini-latest
codex-mini-latest is the newer release (May 15, 2025, against March 2025 for Command A).
Specifications side by side
| codex-mini-latest | Command A | |
|---|---|---|
| Provider | OpenAI | Cohere |
| Category | Language models | Language models |
| Status | Deprecated | Generally available |
| Headline price | No data | No data |
| Input | No data | No data |
| Output | No data | No data |
| Cached input | No data | No data |
| Context window | 200k | 256k |
| Max output | 100k | No data |
| Released | May 15, 2025 | March 2025 |
| Knowledge cutoff | June 2024 | No data |
| Licence | Proprietary | Proprietary |
| Capabilities | Vision, Reasoning, Tool calling, Structured output, Batch API | Tool calling, Structured output |
| API model id | codex-mini-latest | command-a-03-2025 |
Benchmarks side by side
Leader in bold.
| Benchmark | codex-mini-latest | Command A |
|---|---|---|
| Terminal-Bench Hard | No data | 0.8% |
| GPQA Diamond | No data | 52.7% |
| Humanity's Last Exam | No data | 4% |
| IFBench (instruction following) | No data | 36.5% |
| τ²-Bench (agentic tool use) | No data | 15.2% |
| Long-context reasoning (AA-LCR) | No data | 21.3% |
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 codex-mini-latest or Command A?
Choose codex-mini-latest for images as input and the latest release. Choose Command A for very long inputs.
Which is cheaper, codex-mini-latest or Command A?
A price comparison is not possible: one of them has no comparable published price.
Which has the larger context window, codex-mini-latest or Command A?
Command A reads more per request: 256k tokens against 200k.
What is the difference between codex-mini-latest and Command A?
codex-mini-latest is made by OpenAI and Command A by Cohere. A price comparison is not possible: one of them has no comparable published price. Command A reads more per request: 256k tokens against 200k. codex-mini-latest is the newer model (May 15, 2025, against March 2025). Only codex-mini-latest offers vision, reasoning, batch api.
Which is newer, codex-mini-latest or Command A?
codex-mini-latest was released on May 15, 2025 and Command A on March 2025.