Moduck

Mistral: Mistral Small 4

Fast Mistral production model for chat, extraction, and cost-sensitive agents

Model lab
Mistral
Model family
mistral-small

Model resources

Modalitiestext, image → text
Context window256,000
Maximum output256,000
InputUSD 0.12 / 1M tokens
OutputUSD 0.48 / 1M tokens

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to moduck/mistral-ai/mistral-small-2603.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "moduck/mistral-ai/mistral-small-2603"

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 Small 4 API Pricing

TypePrice information
InputUSD 0.12 / 1M tokens
OutputUSD 0.48 / 1M tokens
Cached inputUSD 0.012 / 1M tokens

Benchmarks

Non-reasoning

Intelligence Index · v4.39
Coding Index—
Agentic Index—
BenchmarkScoreMeasurementSource
Artificial Analysis Coding Index24.3index · Date: 2026-06-01
SciCode38percent correct · Date: 2026-06-01
Terminal-Bench Hard17.4success rate · Date: 2026-06-01

Performance

Measured on the Moduck gateway across live traffic, hour by hour over the last 24 hours. Time to first token is how long before anything appears; throughput is how fast the answer is written after that; end-to-end latency is the whole round trip. Figures are medians unless the card says otherwise.

Artificial Analysis measurement · Non-reasoning

Output speed153.69 tokens/s
Time to first token0.91 s
Time to first answer token—
End-to-end response time—
Measurement variantOutput speedTime to first tokenTime to first answer tokenEnd-to-end response time
Non-reasoning153.69 tokens/s0.91 s——

Performance trends

Throughput153.69 tok/sCurrent
Time to first token0.91 sCurrent
End-to-end latency6.9 sCurrent
Throughput
Current153.69 tok/s
Window average156.6 tok/s
Time to first token
Current0.91 s
Window average0.9 s
End-to-end latency
Current6.9 s
Window average7.5 s
Tail latency (P99)
Current14.6 s
Window average16.8 s
Prompt cache hit rate
Current31.1%
Window average23.3%
Error rate
Current0.0%
Window average0.2%

Availability

Uptime is the share of time at least one provider serving this model responded. Availability is stricter: the share of requests actually served. A provider that answers but fails part of the traffic lowers availability without lowering uptime. Both cover the last three days.

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 Small 4 Compare models

ModelInput priceOutput priceContext windowCapabilities
Mistral Small 4This pageUSD 0.12 / 1M tokensUSD 0.48 / 1M tokens256,000Text output · Reasoning · Tool calling
Mistral Small (latest)USD 0.12 / 1M tokensUSD 0.48 / 1M tokens256,000Text output · Reasoning · Tool calling
Mistral Small 3.2USD 0.06 / 1M tokensUSD 0.16 / 1M tokens128,000Text output · Tool calling
Mistral Small 3.2 24BUSD 0.075 / 1M tokensUSD 0.2 / 1M tokens256,000Text output · Tool calling
Mistral Small 3.1 24BUSD 0.08 / 1M tokensUSD 0.24 / 1M tokens128,000Text output · Tool calling

Model specifications

Input
text, image
Output
text
Context window
256,000
Maximum output
256,000
Release date
2026-03-16
Attachments
Yes
Reasoning
Yes
Tool calling
Yes
Temperature setting
Yes
Open weights
Yes

Frequently asked questions

What is Mistral Small 4 for?

Fast Mistral production model for chat, extraction, and cost-sensitive agents

What inputs and outputs does Mistral Small 4 support?

Recorded inputs: text, images; outputs: text.

How is Mistral Small 4 priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.12 / 1M tokens; Output USD 0.48 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Mistral Small 4?

Current model records list Context window 256,000 tokens; Maximum output 256,000 tokens.

What model parameter does the Quickstart use?

The example uses moduck/mistral-ai/mistral-small-2603. This is a cataloged Moduck public or reserved ID; check your account’s available models before calling it.

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.