GPT-6 Luna vs Mistral Large 4
GPT-6 Luna (OpenAI) and Mistral Large 4 (Mistral) are listed at different prices. GPT-6 Luna costs less: $0.10 per 1M input tokens and $0.50 per 1M output tokens, against $0.70 and $2.10 for Mistral Large 4. GPT-6 Luna has the larger context window, 1,050,000 tokens against 1,048,576 for Mistral Large 4. GPT-6 Luna charges $0.20 and $0.75 per 1M once a prompt passes 272,000 tokens; Mistral Large 4 keeps one price across its window. GPT-6 Luna accepts text, images and files and produces text; Mistral Large 4 accepts text and images and produces text.
OpenAI: GPT-6 Luna accepts files, images, and text, while Mistral: Mistral Large 4 accepts images and text. Both produce text and support tools, structured outputs, response formats, and reasoning; their context windows are close in size, while their maximum output limits differ.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Maker | OpenAI | Mistral |
| Added to catalog | 22 Sep 2026 | 6 Oct 2026 |
| Input, per 1M tokens | $0.10 | $0.70 |
| Output, per 1M tokens | $0.50 | $2.10 |
| Input above 272K tokensPer 1M; long prompts | $0.20 | $0.70 |
| Output above 272K tokens | $0.75 | $2.10 |
| Cached input read, per 1M | $0.01 | $0.07 |
| Context windowTokens | 1,050,000 | 1,048,576 |
| Max outputTokens | 128,000 | 262,144 |
| Accepts | file, image, text | image, text |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | Yes |
| Reasoning effort control | Yes | Yes |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0002 | $0.0010 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0029 | $0.019 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0040 | $0.025 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.016 | $0.108 |
Which to choose
Choose GPT-6 Luna if
- Input tokens cost less: $0.10 against $0.70 per 1M
- Output tokens cost less: $0.50 against $2.10 per 1M
- Your prompts often run past 272K tokens: $0.20 against $0.70 per 1M input tokens there
- Cached input costs less: $0.01 against $0.07 per 1M
- You need the larger context window: 1,050,000 tokens against 1,048,576
- It has to read files, which the other model does not
Choose Mistral Large 4 if
- You need longer answers in one response: 262,144 tokens against 128,000
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.