MistralText Generation/v1/ai/chat

Mistral Medium 3.5 API

Access Mistral Medium 3.5 through one API key. Mistral's balanced mid-tier model.

Mistral's balanced mid-tier model. Strong general reasoning, coding, and multilingual performance with a 256K token context window.

Full Docs Get API Key — Free $5 Credit

No credit card required. Takes 30 seconds.

Mistral Medium 3.5 API pricing

Pay per request from your YepAPI balance — no subscription, no monthly minimum. Prices updated September 27, 2026.

Token type	Price
Input	$2.22 / 1M tokens
Output	$11.08 / 1M tokens
Context window	262K tokens

What it costs	Per job	Per 1,000
Chat reply1K input + 500 output tokens	$0.0078	$7.76
RAG answer8K input + 800 output tokens	$0.027	$26.62
Agent step with tools30K input + 2K output tokens	$0.089	$88.76
Long document summary100K input + 2K output tokens	$0.244	$244.16

2,400+

Developers

1.2M+

API calls served

100+

Endpoints

$0.01

Per call

Yep, that's it.

Try it live

Send a message and see Mistral Medium 3.5 respond in real time.

POST/v1/ai/chatmistralai/mistral-medium-3-5

Message *

Max Tokens

Maximum tokens in the response.

Stream

Real-time tokens

Hit "Send Request" to see the response

Mistral Medium 3.5 specs

Provider	Mistral
Model ID	mistralai/mistral-medium-3-5
Endpoint	/v1/ai/chat
Type	Text Generation
Context window	262K tokens
Max output	16K tokens
Reasoning	No
OpenAI-compatible	Yes — /v1/ai/chat/completions

How to get a Mistral Medium 3.5 API key

1
Create a free account
Sign up at yepapi.com with Google or email. It takes about 30 seconds and needs no card.
2
Create an API key
Open the dashboard, go to API Keys and create a key. Copy it — it starts with yep_sk_.
3
Call Mistral Medium 3.5
Send a request to /v1/ai/chat with the x-api-key header and model "mistralai/mistral-medium-3-5".
4
Pay as you go
Usage is billed per request from your balance. Top up any amount; there is no subscription.

Strengths

✓

Balanced mid-tier model

Mistral's mid-tier model balancing capability and cost, strong on general reasoning, coding, and multilingual tasks, with up to 16,384 output tokens.

✓

256K token context

A 262,144-token context window handles long documents and sizeable codebases in a single request — ample for most production workloads.

✓

Strong coding & multilingual

Reliable code generation and debugging plus solid European-language coverage, reflecting Mistral's multilingual focus.

✓

Efficient price-to-performance

At $2.22 / $11.08 per 1M tokens it offers competitive mid-tier quality at a rate well below flagship models for everyday reasoning and coding.

Quick start

Copy this snippet and start making calls with Mistral Medium 3.5.

const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
  method: 'POST',
  headers: {
    'x-api-key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    "model": "mistralai/mistral-medium-3-5",
    "messages": [
      {
        "role": "user",
        "content": "Explain API gateways in 2 sentences."
      }
    ],
    "maxTokens": 256
  }),
});
const { data } = await res.json();
console.log(data.message.content);

Mistral Medium 3.5 vs similar models

Every model below runs on the same API key — switch by changing the model ID.

Model	Provider	Price	Context
Mistral Medium 3.5	Mistral	$2.22 in / $11.08 out per 1M	262K
Mistral Small 4	Mistral	$0.22 in / $0.89 out per 1M	262K
Devstral 2	Mistral	$0.59 in / $2.95 out per 1M	262K
Mistral Large 4	Mistral	$2.01 in / $6.17 out per 1M	1.0M
Nemotron 3 Super	NVIDIA	$0 in / $0 out per 1M	262K
Qwen3.7 Flash	Qwen	$0.04 in / $0.19 out per 1M	1M
Solar Mini 4	Upstage	$0.07 in / $0.30 out per 1M	524K
Nemotron 3.5 Lightning	NVIDIA	$0.10 in / $0.30 out per 1M	262K

Why use Mistral Medium 3.5 through YepAPI?

✓One API key for all models — no separate accounts

✓OpenAI SDK compatible — just change the base URL

✓No monthly minimums — pay per token

✓Switch models with one line of code

✓Full provider passthrough — citations, search results, and all extras included

✓Streaming and non-streaming support on every model

✓Works with Cursor, Claude, LangChain, and any LLM tool

✓Unified billing across all providers

Mistral Medium 3.5 API — pricing, context window & access

Mistral Medium 3.5 is Mistral's balanced mid-tier model, with strong general reasoning, coding, and multilingual performance backed by a 256K-token context window and up to 16,384 output tokens. It targets the workhorse tier between small and flagship models.

YepAPI serves Mistral Medium 3.5 over an OpenAI-compatible endpoint with one key that also reaches Mistral Small 4, the coding-focused Devstral 2, Claude, Gemini, Grok, Qwen, and Perplexity Sonar, plus SEO, SERP, and scraping APIs.

What is Mistral Medium 3.5?

Mistral Medium 3.5 is the mid-tier model from Mistral, the European AI lab. It is built to be a balanced workhorse — strong on general reasoning, coding, and multilingual tasks without the cost of a flagship. It carries a 262,144-token context window and returns up to 16,384 output tokens, which covers long documents and most codebases. With particular strength across European languages, it suits teams that want capable, efficient general-purpose inference and value Mistral's multilingual and data-residency positioning.

Build with Mistral Medium 3.5 via YepAPI

Call Mistral Medium 3.5 through YepAPI's OpenAI-compatible /v1/ai/chat endpoint with the model set to mistral-medium-3-5. Existing OpenAI SDK code works after a base-URL and model-name change. For cheaper bulk work, switch to Mistral Small 4; for heavy coding, Devstral 2 — each is a one-string change. The same key reaches Claude, Gemini, and Sonar, so multi-model routing needs no extra integration.

Mistral Medium 3.5 API pricing — $2.22 / $11.08 per 1M tokens

Mistral Medium 3.5 costs $2.22 per 1M input tokens and $11.08 per 1M output tokens on YepAPI. That sits comfortably in the mid tier — above the ultra-cheap Small model but well under flagship reasoning models — making it a sensible default for general production traffic that needs decent quality at a controlled cost. Billing is per token with no minimums.

Mistral Medium 3.5 for multilingual general-purpose work

Medium 3.5 is well suited to everyday production tasks with a European or multilingual slant: customer support, content generation, summarization, and general coding across languages. Its 256K-token window handles long inputs, and its balanced tuning keeps quality high without flagship costs. For teams that prefer a European model or need strong non-English coverage at a mid-tier price, it is a natural default.

Try Mistral Medium 3.5 free

New YepAPI accounts get $5 in free credit with no card required. It is enough to wire Mistral Medium 3.5 into your app and run real multilingual or coding traffic before deciding on paid usage.

Start generating in 30 seconds

$5 free credit on signup. No credit card required. Pay per call.

Get API Key

What developers say

“Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.”
Marcus T.
SEO Platform Founder

“One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.”
Priya S.
Full-Stack Developer

“The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.”
Jake R.
Indie Hacker

Frequently asked questions

Mistral's balanced mid-tier model. Strong general reasoning, coding, and multilingual performance with a 256K token context window.

Mistral Medium 3.5 costs $2.22 per 1M input tokens and $11.08 per 1M output tokens through YepAPI, billed per request with no monthly fee. For example, a chat reply (1K input + 500 output tokens) costs about $0.0078.

Sign up at yepapi.com (Google or email, about 30 seconds), open the dashboard and create an API key. The same key works for Mistral Medium 3.5 and every other model — no separate Mistral account or waitlist.

New YepAPI accounts in most countries get free signup credit, enough to test Mistral Medium 3.5 without a card. After that you pay per request at the rates above — there is no subscription.

Use "mistralai/mistral-medium-3-5" as the model on /v1/ai/chat. The short alias "mistral-medium" also works.

Yes. Point the OpenAI SDK at https://api.yepapi.com/v1/ai with your YepAPI key and set model to "mistralai/mistral-medium-3-5". Streaming works the same way, so existing OpenAI code only needs the base URL and key changed.

Mistral Medium 3.5 supports a 262K token context window with up to 16K output tokens per request.