Magistral Small
Last verified August 24, 2026 · Mistral pricing ↗$0.500/1M input · $1.50/1M output · 40K context · Mistral
Magistral Small last cost $0.500 per 1M input tokens and $1.50 per 1M output tokens from Mistral, with a 40K-token context window. A typical chat reply (1,500 tokens in, 400 out) costs $0.0014, or $13.50 per 10,000 requests.
Not generally available
Mistral has shut Magistral Small down. You cannot buy it at the rate below. The price is kept so past spend and old estimates still reconcile, and it is excluded from the calculator’s default model list and from every ranking.
Mistral’s own page ↗Count Tokens
Estimate Monthly Cost
Monthly Cost Estimator
Pick a preset above or enter custom usage
What Magistral Small Costs Per Request
At $0.500 per 1M input and $1.50 per 1M output tokens, before caching or batch discounts.
| Workload | Input / output tokens | Per request | Per 10,000 requests |
|---|---|---|---|
| Chat reply | 1,500 / 400 | $0.0014 | $13.50 |
| RAG answer over retrieved docs | 8,000 / 600 | $0.0049 | $49.00 |
| Coding-agent step | 30,000 / 2,000 | $0.018 | $180.00 |
Magistral Small vs Similarly Priced Models
Nearest buyable models by price, with the RAG answer above (8,000 in / 600 out) priced on each.
| Model | Input /1M | Output /1M | Context | RAG answer |
|---|---|---|---|---|
| Magistral Small Mistral | $0.500 | $1.50 | 40K | $0.0049 |
| Mistral Large 3 Mistral | $0.500 | $1.50 | 262K | $0.0049 |
| GPT-4.1 Mini OpenAI | $0.400 | $1.60 | 1.0M | $0.0042 |
| Qwen3.7 Plus Alibaba | $0.400 | $1.60 | 1.0M | $0.0042 |
Alternatives to Magistral Small
Pricing Details
Price History
Frequently Asked Questions
Common questions about Magistral Small pricing and usage