How much does Mistral Small cost through Final Router?

$0.15 per million input tokens and $0.6 per million output tokens - the provider's own list price, with no markup on tokens. A 5.5% fee applies only when you add credits.

Does Mistral Small train on my data?

No. On the endpoint Final Router calls, Mistral does not train on your prompts. Data is processed in EU.

How do I call Mistral Small?

Point any OpenAI-compatible client at https://finalrouter.com/api/v1 with your Final Router key and set model to "mistral/mistral-small-latest". Your existing code does not change.

Mistral · model

Mistral Small

Low cost, Low latency. Called through Final Router's one OpenAI-compatible endpoint at Mistral's list price, with no markup on tokens.

Model id: mistral/mistral-small-latest

Input price$0.15per 1M tokens

Output price$0.6per 1M tokens

Context window262Ktokens

Typical speed260msmedian

Quality score70/100composite

ProviderMistralprocessed in EU

Verified 2026-08-21Mistral's own list price, with no markup on tokens - a 5.5% fee applies only when you add credits.

Call Mistral Small in one line

Mistral Small speaks through the same OpenAI-compatible endpoint as every other model. Point your existing client at Final Router, set the model id, and you also get automatic fallback, spend caps and usage tracking - none of which the provider gives you directly.

Call Mistral Small

from openai import OpenAI

client = OpenAI(
    api_key="fr_live_...",                     # your Final Router key
    base_url="https://finalrouter.com/api/v1"  # the only line you change
)

resp = client.chat.completions.create(
    model="mistral/mistral-small-latest",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Data & residency

Mistral is a Paris company directly subject to the GDPR, and La Plateforme processes in the EU by default with no configuration. Their own documentation notes temporary transfers for some features and subprocessors, so this is EU by default rather than EU without exception.

Training: not used to train the model. Retention: Not used for training on the paid API; opt-in schemes exist separately.

Mistral's policy, read 2026-08-21 →

Route it, don't pin it

Name Mistral Small as your first choice and let a policy fall back to another model when the provider is down - your request still gets answered, and the log shows exactly what happened.

Start free

Mistral Small FAQ

How much does Mistral Small cost through Final Router?: $0.15 per million input tokens and $0.6 per million output tokens - the provider's own list price, with no markup on tokens. A 5.5% fee applies only when you add credits.
What is Mistral Small's context window?: 262,144 tokens.
Does Mistral Small train on my data?: No. On the endpoint Final Router calls, Mistral does not train on your prompts. Data is processed in EU.
How do I call Mistral Small?: Point any OpenAI-compatible client at https://finalrouter.com/api/v1 with your Final Router key and set model to "mistral/mistral-small-latest". Your existing code does not change.

Compare with

All comparisons

Mistral Small vs Gemini 2.5 Flash Mistral Small vs DeepSeek V4 Flash Mistral Small vs GPT-5 mini Mistral Small vs Muse Spark 1.1

Gemini 2.5 FlashGoogle

$0.3 in$2.5 out1.048576M ctx

Very fast · Long context · Summarization

DeepSeek V4 FlashDeepSeek

$0.22 in$0.66 out1M ctx

Cheapest · Huge context · Tool use

GPT-5 miniOpenAI

$0.25 in$2 out400K ctx

Fast · Cheap · Classification

Muse Spark 1.1Meta

$1.25 in$4.25 out1.048576M ctx

Coding · Huge context

mistral-small-latestLatency and quality are seed figures used for routing order, not billing. Prices are what you are charged.