← All models
M
Magistral Medium
Mistral
Mistral's reasoning model — strong for complex analytical and math tasks
Input price$2.00 / 1M tokens
Output price$5.00 / 1M tokens
Context window128k tokens
Last updated2026-04-20
Quick calculator
Per request
$0.004500
Daily
$45.00
Monthly
$1,350.00
per month · 30-day estimate
Yearly
$16,425.00
Tips to reduce cost
- →Use prompt caching to reuse repeated system prompts
- →Trim whitespace and reduce verbose instructions
- →Use a smaller model for classification or routing tasks
- →Batch async requests to get 50% discount (OpenAI/Anthropic)
- →Cache identical requests at the application layer
Similar models from Mistral
Compared at your current token settings
About Magistral Medium
Magistral Medium is a premium large language model from mistral, priced at $2/1M input tokens and $5/1M output tokens. It is 18% cheaper than the market average and best suited for math & analysis. The 128k context window handles long documents, extended conversations, and large code files comfortably.
For most production workloads, the cost breakdown is dominated by input tokens (system prompts, context, retrieved documents) rather than output. At this price point, Magistral Medium is positioned for use cases where quality justifies the premium over cheaper alternatives.
Frequently Asked Questions
How much does Magistral Medium cost per 1,000 tokens?
Magistral Medium costs $0.0020 per 1,000 input tokens and $0.0050 per 1,000 output tokens.
What is Magistral Medium's context window?
Magistral Medium supports a context window of 128k tokens, which is suitable for long documents and multi-turn conversations.
How does Magistral Medium compare to GPT-4o on price?
Magistral Medium is 18% cheaper than the market average on input tokens. At $2/1M input vs $2.50/1M for GPT-4o, the cost difference becomes significant at scale — 10,000 requests/day with 1,000 input tokens each costs $600/month with Magistral Medium vs $750/month with GPT-4o.