Mistral: Mistral Medium 3

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Model lab: Mistral
Model family: mistral-medium

Modalitiestext, image, pdf → text

Context window131,072

Maximum output104,857

InputUSD 0.32 / 1M tokens

OutputUSD 1.6 / 1M tokens

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to mistral/mistral-medium-3.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "mistral/mistral-medium-3"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Mistral Medium 3 API Pricing

Type	Price information
Input	USD 0.32 / 1M tokens
Output	USD 1.6 / 1M tokens
Cached input	USD 0.032 / 1M tokens

Benchmarks

Intelligence Index · v4.39

Coding Index—

Agentic Index—

Performance

Output speed45.63 tokens/s

Time to first token2.47 s

Time to first answer token—

End-to-end response time—

Performance trends

Throughput45.63 tok/sCurrent

Time to first token2.47 sCurrent

End-to-end latency7.2 sCurrent

Throughput

Current45.63 tok/s

Window average50.3 tok/s

Time to first token

Current2.47 s

Window average2.5 s

End-to-end latency

Current7.2 s

Window average7.5 s

Tail latency (P99)

Current17.2 s

Window average16.4 s

Prompt cache hit rate

Current31.2%

Window average22.5%

Error rate

Current0.0%

Window average0.2%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Mistral Medium 3 Compare models

Model	Input price	Output price	Context window	Capabilities
Mistral Medium 3This page	USD 0.32 / 1M tokens	USD 1.6 / 1M tokens	131,072	Text output · Tool calling
Mistral Medium 3.5	USD 1.2 / 1M tokens	USD 6 / 1M tokens	262,144	Text output · Reasoning · Tool calling
Mistral Medium 3.1	USD 0.32 / 1M tokens	USD 1.6 / 1M tokens	131,072	Text output · Tool calling
Mistral Medium (latest)	USD 0.32 / 1M tokens	USD 1.6 / 1M tokens	262,144	Text output · Reasoning · Tool calling
Mistral Medium 3.5	USD 1.38 / 1M tokens	USD 5.52 / 1M tokens	262,144	Text output · Reasoning · Tool calling

Model specifications

Input: text, image, pdf
Output: text
Context window: 131,072
Maximum output: 104,857
Release date: 2025-05-07
Attachments: Yes
Reasoning: No
Tool calling: Yes
Structured output: Yes
Temperature setting: Yes
Open weights: No

Frequently asked questions

What is Mistral Medium 3 for?

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

What inputs and outputs does Mistral Medium 3 support?

Recorded inputs: text, images, PDF; outputs: text.

How is Mistral Medium 3 priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.32 / 1M tokens; Output USD 1.6 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Mistral Medium 3?

Current model records list Context window 131,072 tokens; Maximum output 104,857 tokens.

What model parameter does the Quickstart use?

The example uses mistral/mistral-medium-3. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.