Ministral 3 8B pricing
Mistral AI · API id ministral-8b-2512 · verified 2026-10-18
| Input | $0.15 |
| Cached input (cache hit) | $0.015 |
| Cache write | — |
| Output | $0.15 |
| Batch discount | 50% |
| Context window | 256,000 tokens |
| Max output | — |
USD per 1M tokens unless noted. Official source
Estimate your workload on Ministral 3 8B →
What Ministral 3 8B costs for real workloads
| Workload | Ministral 3 8B | Claude Haiku 5.5 | GPT-6 Luna | Mistral Small 4 | Codestral |
|---|---|---|---|---|---|
| 10,000 chatbot replies 2,000 input + 400 output tokens each, 50% of the prompt cached | $2.25 | $3.10 | $3.10 | $4.05 | $6.90 |
| One 30-step coding agent run 12K system + tools prompt, 1K output and 3K tool result per step, caching on | $0.05 | $0.12 | $0.05 | $0.07 | $0.13 |
| 1M documents classified (batch) 600 input + 20 output tokens each, batch API where available | $46.50 | $35.00 | $35.00 | $51.00 | $99.00 |
Compared with the cheapest other small models. Change the numbers in the calculator.
Billing notes
Alias ministral-8b-latest. 14B ($0.20/$0.20) and 3B ($0.10/$0.10) variants also offered. Batch 50% off per mistral.ai/pricing. Max output not published.
Where Ministral 3 8B ranks by use case
Position by cost among all models that fit each workload (1 = cheapest).
- Cheapest LLM for coding agents: #2 of 36 (Per run (cached): $0.05)
- Cheapest LLM for RAG chatbots: #3 of 36 (Per 1,000 answers: $0.76)
- Cheapest LLM for batch classification and extraction: #3 of 36 (Classify 1M docs: $46.50)
- Cheapest LLM for high-volume customer support: #1 of 36 (Per 1,000 replies: $0.22)
Counting tokens for a prompt? The token counter estimates Ministral 3 8B tokens (xAI, DeepSeek, Mistral tokenizer, estimated) and input cost.
Other Mistral AI models
- Mistral Large 4: $0.68 / $2.09
- Mistral Medium 3.5: $1.50 / $7.50
- Codestral: $0.30 / $0.90
- Mistral Small 4: $0.15 / $0.60
FAQ
How much does Ministral 3 8B cost per 1M tokens?
Ministral 3 8B costs $0.15 per 1M input tokens and $0.15 per 1M output tokens at standard rates (verified 2026-10-18).
Does Ministral 3 8B support prompt caching?
Yes. Cached input is billed at $0.015 per 1M tokens.
Is there a batch discount for Ministral 3 8B?
Yes. The batch API is 50% cheaper than standard requests.
What is the context window of Ministral 3 8B?
256,000 tokens.