Side-by-side comparison
GPT-5 Codex vs Mistral Medium 3.5
OpenAI
GPT-5 Codex
👁 Vision
🔧 Tools
{} JSON
Input / 1M
$1.2500
Output / 1M
$10.0000
Mistral
Mistral Medium 3.5
👁 Vision
🔧 Tools
{} JSON
Input / 1M
$1.5000
Output / 1M
$7.5000
| GPT-5 Codex | Mistral Medium 3.5 | |
|---|---|---|
| Provider | OpenAI | Mistral |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 400,000 | 262,144 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | vision, tools, json_mode | vision, tools, json_mode |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 1.2500 | 1.5000 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 10.0000 | 7.5000 |
Frequently asked questions
Which is cheaper, GPT-5 Codex or Mistral Medium 3.5?
Mistral Medium 3.5 is cheaper than GPT-5 Codex on a 50/50 input/output blend by about $1.125 per 1M tokens. Exact savings depend on your input-vs-output ratio — use the cost calculator on this page for a workload-specific estimate.
Which has a larger context window, GPT-5 Codex or Mistral Medium 3.5?
GPT-5 Codex has the larger context window at 400k tokens versus 262k tokens for Mistral Medium 3.5. That means GPT-5 Codex can ingest about 1.5x as much text per request.
What is the difference between GPT-5 Codex and Mistral Medium 3.5?
GPT-5 Codex comes from OpenAI; Mistral Medium 3.5 comes from Mistral. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.