← model directory

mistralai

Mistral: Mistral Small 3

mistralai/mistral-small-24b-instruct-2501

↓ runs free on your own hardware

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...

specs & pricing
Type
text
Provider
mistralai
Model ID
mistralai/mistral-small-24b-instruct-2501
Context window
33K tokens
Self-hostable
Yes — runs on your own GPU
Input price
$0.055 / 1M tokens
Output price
$0.088 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.

What it costs to run

cloud · 1M in + 1M out

$0.14

$0.055 for a million input tokens plus $0.088 for a million output tokens, billed from credits only when a request fails over to the cloud.

your hardware

$0 / token

Served from a workstation or on-prem server you own, there is no per-token fee — the marginal cost is power.

Run it on your own hardware

Estimated GPU memory for Mistral: Mistral Small 3 (24B parameters), for the weights alone — add room for the context cache.

Q4_K_M
~14.4 GBfits a 16 GB card
Q8_0
~24.4 GBfits a 32 GB card
FP16 / BF16
~45.5 GBfits a 48 GB card

Install the agent on the machine and it dials out to the gateway over a single WebSocket — no port forwarding or inbound firewall rules. Requests for this model go to your node first and fail over to the cloud only when it can't serve.

/// initialize

Call Mistral: Mistral Small 3 through one OpenAI-compatible endpoint.

Serve it from hardware you own, with cloud failover when your nodes are busy or offline.

no credit card · 2 nodes free · openai-compatible

Frequently asked questions

What is the context window of Mistral: Mistral Small 3?
Mistral: Mistral Small 3 accepts up to 32,768 tokens (33K) of context per request.
How much does Mistral: Mistral Small 3 cost per million tokens?
Through Wide Area Intelligence, Mistral: Mistral Small 3 costs $0.055 per 1M input tokens and $0.088 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $0.14.
Can I run Mistral: Mistral Small 3 on my own hardware?
Yes — Mistral: Mistral Small 3 is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 14.4 GB of GPU memory, plus room for the context cache — it fits a single 16 GB card. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.

More from mistralai

← browse all models