OpenAI: GPT-6.1 Terra vs Mistral: Mistral Large 4
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-02.
| OpenAI: GPT-6.1 Terra | Mistral: Mistral Large 4 | |
|---|---|---|
| Vendor | openai | mistralai |
| Quality Score | 100 | 100 |
| Input Price | $1.00/M | $0.70/M |
| Output Price | $5.00/M | $2.10/M |
| Context Window | 1,050,000 | 1,048,576 |
| Max Output | 128,000 | 262,144 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Mistral Large 4 costs $1.23 and GPT-6.1 Terra costs $2.25, so Mistral Large 4 is about 1.8 times cheaper for the same work.
Both take in a similar amount of text: 1,050,000 and 1,048,576 tokens, about 1,575 and 1,573 pages.
Across the 10 tasks where they differ, Mistral Large 4 on 10 (SQL Generation, Code Completion, Code Documentation and others).
Pick Mistral Large 4 if you need lower cost or the stronger all-round task scores.
Costs use current list prices per million tokens; page counts assume about 0.75 words per token and 500 words per page.
Who wins by task?
| Task | OpenAI: GPT-6.1 Terra | Mistral: Mistral Large 4 |
|---|---|---|
| SQL Generation | 133 | 133 |
| Code Completion | 118 | 131 |
| Code Documentation | 130 | 131 |
| Regex Writing | 118 | 119 |
| CSV / Spreadsheet Cleanup | 133 | 133 |
| JSON Extraction | 122 | 131 |
| Bulk Data Labeling | 120 | 129 |
| Long-Document Summarization | 137 | 137 |
| Short-Form Summarization | 114 | 123 |
| Blog Post Writing | 121 | 121 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →