AgenticMarket
MistralOpen WeightReleased: 2026-04-30Medium 3.5
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
ARCHITECTURE & LIMITS
BENCHMARK EVALUATIONS & CODE METRICS
Verified scores from SWE-bench and Artificial Analysis.
Independent coding benchmark evaluating syntax, algorithms, and code completion
Broad multi-domain reasoning, science, and knowledge retrieval
Autonomous multi-step tool use, API calling, and task execution
TOKEN COST CALCULATOR
Estimate production API costs for Medium 3.5.
COMMUNITY ENGINEERING EVALUATIONS
Verified ratings across 4 core software engineering dimensions.
Refactoring accuracy, syntax correctness, and adherence to design patterns.
Zero hallucinations, strict constraint compliance, and negative prompt respect.
Time-to-first-token (TTFT) and throughput tokens per second.
Token pricing economics relative to intelligence quality and output volume.
No text reviews submitted yet. Be the first developer to review Medium 3.5!
RECOMMENDED AGENT SKILLS FOR Medium 3.5
boardroom
/cs:boardroom <brief> — 6-phase multi-role deliberation across the C-suite with Phase 2 isolation, critic pre-screen, and synthesis. Outputs a board memo. Use when a decision spans multiple executive domains — e.g. a pricing change touching finance, positioning, and product, or a raise-vs-cut runway call.
FREQUENTLY ASKED QUESTIONS ABOUT Medium 3.5
What are the input and output token prices for Medium 3.5?+
Medium 3.5 costs $1.50 per 1M input tokens and $7.50 per 1M output tokens.
Does Medium 3.5 support tool calling and agent execution?+
Yes, Medium 3.5 natively supports tool calling, parallel function execution, and structured agent workflows.
What is the context window of Medium 3.5?+
Medium 3.5 features an active context window of 262,144 tokens with a maximum single-turn output of 209,715 tokens.
What AI Agent Skills work best with Medium 3.5?+
Because Medium 3.5 is optimized for agentic tool calling and multimodal vision and code reasoning, it pairs well with Agent Skills like Boardroom, SEO Audit, and UI/UX Pro Max.