OpenAI: GPT-6.1 Terra (batch) vs Mistral: Mistral Large 4

For a sample job of 1 million input tokens and 250,000 output tokens, GPT-6.1 Terra (batch) costs $1.12 and Mistral Large 4 costs $1.23, so GPT-6.1 Terra (batch) is slightly 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 1 tasks where they differ, Mistral Large 4 on 1 (Bulk Data Labeling).

Pick GPT-6.1 Terra (batch) if you need lower cost.

Costs use current list prices per million tokens; page counts assume about 0.75 words per token and 500 words per page.