Mistral Medium 3.1 (batch)
Mistral Medium 3.1 · Batch tier (Batch)
Asynchronous batch tier: discounted offline batch requests with high throughput and relaxed latency — ideal for large-scale non-real-time workloads.
Best for: Large-scale offline inference, cost-sensitive batch jobs, backfills
This page covers the Mistral Medium 3.1 Batch tier, sharing the underlying model capability with its real-time standard tier; the main difference is in billing mode and invocation method. See the Mistral Medium 3.1 standard real-time tier.
Provider：Mistral AI
Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...
Key specs
- Context：131.1K
- Max output：104.9K
- Tokenizer：Mistral
- Released：2025-08-13
Token pricing
- Input price：$0.400 / 1M tokens
- Output price：$2.00 / 1M tokens
- Cache read：$0.040 / 1M tokens
- Blended price：$0.800 / 1M tokens
Modalities
Text, Image, File
Use Cases
- Deep Reasoning & Analysis：Math proofs, logical reasoning, multi-step planning — ideal for research and financial analysis.（≈ $0.016/call）
- Vision Understanding & Generation：Recognize data trends in charts, OCR scanned docs, analyze photos and produce structured reports.（≈ $0.012/call）
- Chat & Support：FAQ auto-response, multi-turn dialogue, emotion detection — e-commerce, finance, gov.（≈ $0.0040/call）
When to pick this model
Signals derived from public pricing and spec fields — not a benchmark. Validate with official docs and your own eval.
- Low input price: cost-effective for tasks that consume large context (RAG, long-doc analysis).
- Long max output (>=30K tokens): strong fit for deep report / essay / document-drafting workflows.
- Multimodal (text+image): fit for image captioning, OCR, chart QA, vision-grounded reasoning.
- File / PDF input support: fit for document parsing, contract review, RAG over private data.
FAQ
- What is the token pricing of Mistral Medium 3.1 (batch)? Input price $0.400 / 1M tokens, output price $2.00 / 1M tokens, blended about $0.800 / 1M tokens. Refer to Mistral AI’s official page for the exact rate.
- What context window does Mistral Medium 3.1 (batch) support? Context window is 131.1K, max output about 104.9K, suitable for long documents, multi-turn chat and complex reasoning.
- What scenarios is Mistral Medium 3.1 (batch) best for? Based on its capability and pricing, Mistral Medium 3.1 (batch) fits best: Deep Reasoning & Analysis, Vision Understanding & Generation, Chat & Support. See the Use Cases section for details and cost estimates.
- What input/output modalities does Mistral Medium 3.1 (batch) support? Supports Text, Image, File modality.
- Is Mistral Medium 3.1 (batch) a free model? Mistral Medium 3.1 (batch) is billed per token, not a free model.
- Which provider offers Mistral Medium 3.1 (batch)? Mistral Medium 3.1 (batch) is offered by Mistral AI.
More models from Mistral AI
Full info：Mistral Medium 3.1 (batch)