Frontier enterprise generalist offering 262K context, multimodal vision, hybrid reasoning, and open weights under attractive $0.40/$2.00 pricing.
Technical Specifications
- Provider
- Mistral AI
- Category
- flagship
- Release Date
- 2026-04
- Batch API Discount
- 50% off async batch
- Consumer Subscription
- Free / Self-Hosted
- Reasoning Effort Control
- Configurable (Low / Med / High)
- Structured Outputs
- Yes
- Output Modalities
- text
- Official Documentation
- Visit Official Docs ↗
Data Privacy, Licensing & Deployment Governance
Official Provider Release Intelligence, API Quotas & Agentic Specs
- Official API Model ID (SDK String)
- mistral-medium-3-5-latest
- Supported SDK & API Protocol
- OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
- Lifecycle & Deprecation Status
- Active GA (Guaranteed support through 2028+)
- Production Rate Limits (RPM & TPM)
- Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
- Long-Context Pricing Tier (>128K / >200K)
- Flat rate ($0.4/1M in) across full 262K window
- Prompt Cache Write & TTL Policy
- Cached input at $0.1/1M tokens
- Computer Use & Browser GUI Agent
- API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
- MCP & Parallel Tool Calling
- Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
- Web Search Grounding & Code Sandbox
- Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools
- Fine-Tuning & Distillation Support
- Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
- Multimodal Tokenization Billing
- Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile)
- Weights Precision & Quantization
- BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
- Minimum GPU VRAM Requirement
- 50 GB VRAM (4-bit Quantized) · 172 GB VRAM (Native BF16)
- Supported Inference Engines
- vLLM, SGLang, Ollama, llama.cpp, TensorRT-LLM, HuggingFace TGI
- System Card & Safety Framework
- Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma)
- Enterprise Compliance (SOC2 / HIPAA / ZDR)
- 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
Mistral Medium 3.5 Cost, Context, Hardware & API Integration
For single-user chat, a $20/mo subscription caps your bill below this API volume.
Break-even point: ~222 requests/day equals $20/month.
Same Monthly Workload Cost Across Popular Reference Models
Live Prompt Paste Tokenizer & Cost Counter
Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.
Hybrid Prompt Routing Cascade Simulator
Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Mistral Medium 3.5:
Benchmark Scores & 6-Axis Capability Radar
- SWE-bench Verified
- 54%
- GPQA Diamond
- 68%
- MMLU-Pro
- 84.5%
- HumanEval
- 92.5%
- Terminal-Bench
- 46%
- AIME
- 78%
- Long-Context Reasoning
- 85%
- Chatbot Arena Elo
- 1370pts
Strengths
- Expansive 262K context capacity with near-zero needle retrieval degradation
- Highly attractive $0.40 in / $2.00 out pricing for an enterprise flagship
- Open-weights availability with native visual and reasoning depth
Limitations & Trade-offs
- Trails proprietary multi-trillion parameter giants on bleeding-edge coding
- Requires dedicated enterprise hardware for full local deployment
Editorial Assessment
Europe's most versatile and cost-effective enterprise foundation model of 2026.
Best for: Enterprise intelligence hubs, sovereign multilingual workflows, and multi-turn analytical agents
Compare Mistral Medium 3.5
Frequently Asked Questions about Mistral Medium 3.5
How much does the Mistral Medium 3.5 API cost per 1M tokens?+
Mistral Medium 3.5 by Mistral AI is priced at $0.4 per 1M input tokens and $2 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.1 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.
Should I use a $20/month subscription or the Mistral Medium 3.5 pay-as-you-go API?+
A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.
How many words and pages fit in Mistral Medium 3.5's context window?+
Mistral Medium 3.5 features a 262K tokens context window, which equals approximately 196,608 English words or ~524 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 32,768 tokens.
Can I run Mistral Medium 3.5 locally on my own GPU (Open Weights)?+
Yes, Mistral Medium 3.5 (Confidential (~80B MoE)) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.
Does Mistral AI train on data sent to the Mistral Medium 3.5 API, and is commercial use allowed?+
100% Isolated when self-hosted on private GPUs or VPC. License tier: Permissive Open-Weights (Apache 2.0 / MIT Commercial). Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.
How does Mistral Medium 3.5 perform on coding and reasoning benchmarks?+
Mistral Medium 3.5 achieves a composite Intelligence Index of 55/100, scoring 54% on SWE-bench Verified, 68% on GPQA Diamond, 84.5% on MMLU-Pro, and 1370 pts on Chatbot Arena Elo.
What is Mistral Medium 3.5 best used for?+
Mistral Medium 3.5 is best suited for: Enterprise intelligence hubs, sovereign multilingual workflows, and multi-turn analytical agents. Assessment: Europe's most versatile and cost-effective enterprise foundation model of 2026.
Mistral AI Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to Mistral AI's flagship reasoning tier:
Mistral Small 4
Devstral 2
Devstral Medium
Devstral Small
Mistral Small 3.2
Mistral Medium 3
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to Mistral Medium 3.5:
The basic unit of text that a language model processes, typically representing about 3 to 4 English characters or roughly 0.75 words. For example, the sentence "Artificial intelligence is fast" breaks down into about 5 tokens.
A standardized evaluation suite used to objectively measure and rank an AI model's capabilities across specific tasks — such as SWE-bench Verified for software engineering, AIME for competitive math, or MMLU for general knowledge.
The maximum number of tokens a model can consider at once — both the input it reads and the output it writes. A 1,000,000-token context window can hold roughly 750,000 English words in a single request.
An AI model trained via reinforcement learning to spend dynamic compute thinking through complex logic, math, and architectural problems before outputting a solution. Examples include OpenAI o1, o3, and DeepSeek R1.
A step-by-step reasoning technique where an AI model generates intermediate problem-solving thoughts before arriving at a final answer. Native reasoning models like OpenAI o3 and DeepSeek R1 use CoT to solve complex math and coding challenges.
The ability of a language model to recognize when an external capability is needed and output structured JSON arguments to invoke external APIs, databases, or terminal commands. The runtime executes the tool and passes results back to the model.
Benchmark scores, token prices, and rate limits evolve rapidly as AI labs release model updates. Always verify current specifications and pricing on the official provider documentation.