Magistral Small API Pricing
Magistral Small is retired. Mistral gives MAGISTRAL-SMALL-2509 a retirement date of July 31, 2026 and names Mistral Small 4 as the alternative - Small 4 is itself described as a hybrid that folds reasoning into the generalist model, which is what made a separate Magistral tier redundant. This archive preserves the last published card: $0.5/M input and $1.5/M output.
Magistral Small API cost calculator.
Live calculator pre-loaded with Magistral Small rates. Tweak spend, output mix, or cache assumptions to compare it with sibling models.
Magistral Small cost on real workloads.
Support assistant
Workflow automation
Knowledge base answer
Classification batch
Counts use a chars-per-token calibration measured on the vendor's own published tokenizer (mistralai/Mistral-Nemo-Instruct-2407, 2026-06-10). English prose is typically within a few percent; code and non-Latin scripts tokenize heavier. For billing-exact counts use the vendor's count-tokens API.
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| Magistral Small Current | $0.50 | $1.50 | $0.58 agentic 92/8 | documented elsewhere | Transparent reasoning |
| Mistral Large 3 | $0.50 cache $0.05 | $1.50 | $0.241 −2.4× | documented elsewhere — not on pricing page | Mistral production workloads |
| Mistral Small 4 | $0.15 cache $0.015 | $0.60 | $0.0842 −6.9× | 256K | Low-cost multimodal chat |
| Magistral Medium | $2.00 | $5.00 | $2.24 retired | documented elsewhere — not on pricing page | Transparent reasoning |
| Ministral 3 14B | $0.20 cache $0.02 | $0.20 | $0.0642 −9.0× | 128K | Mistral production workloads |
| Ministral 3 3B | $0.10 cache $0.01 | $0.10 | $0.0321 −18× | 128K | Mistral production workloads |
| DeepSeek V4.1 Flash | $0.30 cache $0.006 | $1.20 | $0.15 −3.9× | 1M | Budget coding and bulk reasoning |
Magistral Small has published scores on 2 benchmarks we track; its best placing is #97 of 105 on ARC-AGI-2. All of these scores come from independent leaderboards, not from the lab.
| Benchmark | Score | Rank | Leader | Source |
|---|---|---|---|---|
| ARC-AGI-2 Reasoning | 0% ARC Prize verified, best result | #97 of 105 | GPT-6 Astra · 95% | Official leaderboard ARC Prize Foundation |
| ARC-AGI-1 Reasoning | 5% ARC Prize verified, best result | #94 of 99 | 6 tied · 98.5% | Official leaderboard ARC Prize Foundation |
Magistral Small API pricing FAQ.
Practical pricing questions, separated from calculator assumptions.
Q · 01 What is Magistral Small priced at? +
$0.5/M input and $1.5/M output. The page stores USD per-million-token baseline pricing from mistral.ai.Q · 02 Does this page include higher context pricing tiers? +
Q · 03 Is prompt caching priced separately? +
$0.5/M.Q · 04 How is the effective price calculated? +
$0.58/M with only documented cache discounts included.