Very long inputs
Choose codex-mini-latest
codex-mini-latest reads up to 200k tokens per request, against 128k for Command A Vision.
Choose codex-mini-latest for very long inputs. Choose Command A Vision for the latest release.
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Choose codex-mini-latest
codex-mini-latest reads up to 200k tokens per request, against 128k for Command A Vision.
Choose Command A Vision
Command A Vision is the newer release (July 2025, against May 15, 2025 for codex-mini-latest).
| codex-mini-latest | Command A Vision | |
|---|---|---|
| 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 | 128k |
| Max output | 100k | No data |
| Released | May 15, 2025 | July 2025 |
| Knowledge cutoff | June 2024 | No data |
| Licence | Proprietary | Proprietary |
| Capabilities | Vision, Reasoning, Tool calling, Structured output, Batch API | Vision |
| API model id | codex-mini-latest | command-a-vision-07-2025 |
Choose codex-mini-latest for very long inputs. Choose Command A Vision for the latest release.
A price comparison is not possible: one of them has no comparable published price.
codex-mini-latest reads more per request: 200k tokens against 128k.
codex-mini-latest is made by OpenAI and Command A Vision by Cohere. A price comparison is not possible: one of them has no comparable published price. codex-mini-latest reads more per request: 200k tokens against 128k. Command A Vision is the newer model (July 2025, against May 15, 2025). Only codex-mini-latest offers reasoning, tool calling, structured output, batch api.
Command A Vision was released on July 2025 and codex-mini-latest on May 15, 2025.