Mistral: Mistral Embed

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Model lab: Mistral
Model family: mistral-embed

Modalitiestext → text

Context window8,000

Maximum output3,072

InputUSD 0.08 / 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-embed.

import os
import requests

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

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 Embed API Pricing

Type	Price information
Input	USD 0.08 / 1M tokens

Performance

Performance trends

Throughput89.8 tok/sCurrent

Time to first token1.5 sCurrent

End-to-end latency7.7 sCurrent

Throughput

Current89.8 tok/s

Window average90.1 tok/s

Time to first token

Current1.5 s

Window average1.5 s

End-to-end latency

Current7.7 s

Window average7.5 s

Tail latency (P99)

Current14.5 s

Window average16.6 s

Prompt cache hit rate

Current18.2%

Window average24.5%

Error rate

Current2.1%

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 Embed Compare models

Model	Input price	Output price	Context window	Capabilities
Mistral EmbedThis page	USD 0.08 / 1M tokens	Not billed on output	8,000	Text output
Devstral 2	USD 0.32 / 1M tokens	USD 1.6 / 1M tokens	262,144	Text output · Tool calling
Devstral 2 (latest)	USD 0.32 / 1M tokens	USD 1.6 / 1M tokens	262,144	Text output · Tool calling
Codestral 25.08	USD 0.24 / 1M tokens	USD 0.72 / 1M tokens	128,000	Text output · Tool calling
Magistral Small	USD 0.4 / 1M tokens · Context ≤ 128000 tokens · Maximum output 64000 tokens	USD 1.2 / 1M tokens · Context ≤ 128000 tokens · Maximum output 64000 tokens	131,072	Text output · Reasoning · Tool calling

Model specifications

Input: text
Output: text
Context window: 8,000
Maximum output: 3,072
Release date: 2023-12-11
Attachments: No
Reasoning: No
Tool calling: No
Temperature setting: No
Open weights: No

Frequently asked questions

What is Mistral Embed for?

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

What inputs and outputs does Mistral Embed support?

Recorded inputs: text; outputs: text.

How is Mistral Embed priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.08 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Mistral Embed?

Current model records list Context window 8,000 tokens; Maximum output 3,072 tokens.

What model parameter does the Quickstart use?

The example uses mistral/mistral-embed. 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.