Medium 3.5 API

mistralai/mistral-medium-3-5
Medium 3.5 on AIMLAPI.
Context
262K tokens
Input
$2.0631 / 1M tokens
Output
$10.3155 / 1M tokens

How to use Medium 3.5 API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to mistralai/mistral-medium-3-5.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "mistralai/mistral-medium-3-5",
      "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-3-5",
    "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-3-5","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Medium 3.5 API Pricing

TypePrice
Input
$2.0631 / 1M tokens
Output
$10.3155 / 1M tokens

Medium 3.5 Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
SWE-bench Verified
77.6%
Resolving verified real GitHub issuesSourceJuly 13, 2026
Intelligence
14.9
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Coding
46.9
Composite score across standardised coding evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026

Medium 3.5 vs other models

ModelInputOutputContextBest for
Medium 3.5
This page
$2.0631 / 1M tokens
$10.3155 / 1M tokens
262K tokens
Reasoning + agents
$6.5 / 1M tokens
$39 / 1M tokens
1.05M tokens
Reasoning + agents
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$0.65 / 1M tokens
$3.9 / 1M tokens
1.05M tokens
Reasoning + agents

Frequently asked questions

Medium 3.5 has a 262,144 tokens context window.

Medium 3.5 takes image, text as input and returns text.

Use mistralai/mistral-medium-3-5 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

Medium 3.5 is priced at input $2.0631 / 1M tokens, output $10.3155 / 1M tokens.

Yes, Medium 3.5 can stream responses as they are generated.

Yes, Medium 3.5 accepts image input alongside text.

Medium 3.5 was built by Mistral AI.

Yes, it supports function calling, tool use, and parallel tool calls, making it suitable for agentic workflows.

Yes, it includes web search and reasoning capabilities alongside structured output support.

Start building with Medium 3.5

Get API Key
1000+ models, one API.