Very long inputs
Choose codex-mini-latest
codex-mini-latest reads up to 200k tokens per request, against 128k for Codestral.
Codestral vs codex-mini-latest: price, context and capabilities
Choose Codestral for the latest release. Choose codex-mini-latest for very long inputs and images as input.
In short
- 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.
- Codestral is the newer model (August 2025, against May 15, 2025).
- Only codex-mini-latest offers vision, reasoning, structured output, 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; Codestral does not.
Latest release
Choose Codestral
Codestral is the newer release (August 2025, against May 15, 2025 for codex-mini-latest).
Specifications side by side
| Codestral | codex-mini-latest | |
|---|---|---|
| Provider | Mistral AI | 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 | 128k | 200k |
| Max output | No data | 100k |
| Released | August 2025 | May 15, 2025 |
| Knowledge cutoff | No data | June 2024 |
| Licence | Proprietary | Proprietary |
| Capabilities | Tool calling | Vision, Reasoning, Tool calling, Structured output, Batch API |
| API model id | codestral-2508 | codex-mini-latest |
Frequently asked questions
Should I choose Codestral or codex-mini-latest?
Choose Codestral for the latest release. Choose codex-mini-latest for very long inputs and images as input.
Which is cheaper, Codestral or codex-mini-latest?
A price comparison is not possible: one of them has no comparable published price.
Which has the larger context window, Codestral or codex-mini-latest?
codex-mini-latest reads more per request: 200k tokens against 128k.
What is the difference between Codestral and codex-mini-latest?
Codestral is made by Mistral AI and codex-mini-latest by OpenAI. 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. Codestral is the newer model (August 2025, against May 15, 2025). Only codex-mini-latest offers vision, reasoning, structured output, batch api.
Which is newer, Codestral or codex-mini-latest?
Codestral was released on August 2025 and codex-mini-latest on May 15, 2025.