What is Medium 3.1 API?
Medium 3.1 is available through AIMLAPI.
Technical Specifications
- Supported inputs: Image, Text
- Output: Text
- Context window: 131,072 tokens / Max output: —
- Endpoint: /chat/completions
Performance Benchmarks
[embed]
Medium 3.1 API Pricing
- Input: $0.52 / 1M tokens
- Output: $2.6 / 1M tokens
Where to Use Medium 3.1
Coding and code review
Generate, debug, and review code across languages, reading whole files or repos in a single prompt.
Agentic and multi-step workflows
Reliable tool-calling and instruction-following suit agent loops that plan, call tools, and iterate.
Complex reasoning
Extended reasoning improves reliability on multi-step math, logic, and technical analysis.
Long-document analysis
Summarize and extract from contracts, papers, and reports without aggressive chunking.
Code Sample
[embed]
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Mistral Medium 3.1 is documented as suited to software development, including writing, reviewing, debugging, and explaining code. It is also documented for document analysis, such as analyzing reports, specifications, forms, research papers, and other long-form documents.
It is documented for business and knowledge work, including drafting content, analyzing information, summarizing materials, and supporting everyday professional workflows. It is also documented for multimodal analysis, such as interpreting screenshots, charts, diagrams, and other visual information alongside text.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "mistralai/mistral-medium-3.1", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "mistralai/mistral-medium-3.1", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"mistralai/mistral-medium-3.1","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| MMLU-Pro | 74.4% | Multi-discipline knowledge + reasoning (harder MMLU) | Source | July 12, 2026 |
| Intelligence | 9.9 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Coding | 20.5 | Composite score across standardised coding evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Math | 38.3 | Composite score across standardised mathematics evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Medium 3.1 This page | Reasoning + agents | |||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
Medium 3.1 has a 131,072 tokens context window.
Medium 3.1 takes image, text as input and returns text.
Use mistralai/mistral-medium-3.1 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Medium 3.1 is priced at input $0.55016 / 1M tokens, output $2.7508 / 1M tokens, cached input $0.055016 / 1M tokens.
Yes, Medium 3.1 can stream responses as they are generated.
Yes, Medium 3.1 accepts image input alongside text.
Medium 3.1 was built by Mistral AI.
Yes, it includes reasoning as one of its listed capabilities.
Yes, it supports function calling and parallel tool calls.
