Images as input
Choose GPT-5 Chat
GPT-5 Chat accepts images as input; Codestral does not.
Choose GPT-5 Chat for images as input; on the other points the two are level or the data is missing.
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Choose GPT-5 Chat
GPT-5 Chat accepts images as input; Codestral does not.
| Codestral | GPT-5 Chat | |
|---|---|---|
| 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 | 128k |
| Max output | No data | 16k |
| Released | August 2025 | Aug 7, 2025 |
| Knowledge cutoff | No data | September 2024 |
| Licence | Proprietary | Proprietary |
| Capabilities | Tool calling | Vision, Reasoning, Tool calling, Structured output, Batch API |
| API model id | codestral-2508 | gpt-5-chat-latest |
Choose GPT-5 Chat for images as input; on the other points the two are level or the data is missing.
A price comparison is not possible: one of them has no comparable published price.
Both accept 128k tokens per request.
Codestral is made by Mistral AI and GPT-5 Chat by OpenAI. A price comparison is not possible: one of them has no comparable published price. Both accept 128k tokens per request. Only GPT-5 Chat offers vision, reasoning, structured output, batch api.