Vendor

Mistral AI models

20 models with the vendor's list prices per million tokens. None answers on this deployment yet - connect your own provider to route to them.

Models

0 available here

Cheapest (blended)

$0.03

Mistral Nemo

Median list price

$0.43

3:1 input to output per 1M tokens

Strongest

Mistral Large 4

intelligence index 38

Every Mistral AI model

Newest first. Prices are the vendor's published rates per million tokens; click a model for the full specification.

Model	Released	Context	Input / 1M	Output / 1M	Intelligence	Capabilities
Mistral Large 4mistralai/mistral-large-4-0	Oct 6, 2026	1.0M	$1.36	$4.18	38	reasoning tools
Mistral Medium 3.5mistralai/mistral-medium-3-5	Apr 30, 2026	262K	$1.50	$7.50	14	reasoning tools
Mistral Small 4mistralai/mistral-small-2603	Mar 16, 2026	262K	$0.15	$0.60	11	reasoning tools open weights
Devstral 2 2512mistralai/devstral-2512	Dec 9, 2025	262K	$0.40	$2.00	9	tools open weights
Ministral 3 14B 2512mistralai/ministral-14b-2512	Dec 2, 2025	262K	$0.20	$0.20	6	tools open weights
Ministral 3 8B 2512mistralai/ministral-8b-2512	Dec 2, 2025	262K	$0.15	$0.15	6	tools open weights
Ministral 3 3B 2512mistralai/ministral-3b-2512	Dec 2, 2025	131K	$0.10	$0.10	5	tools open weights
Mistral Large 3 2512mistralai/mistral-large-2512	Dec 1, 2025	262K	$0.50	$1.50	9	tools
Voxtral Small 24B 2507mistralai/voxtral-small-24b-2507	Oct 30, 2025	33K	$0.10	$0.30	-	tools open weights
Mistral Medium 3.1mistralai/mistral-medium-3.1	Aug 13, 2025	131K	$0.40	$2.00	9	tools
Codestral 2508mistralai/codestral-2508	Aug 1, 2025	256K	$0.30	$0.90	-	tools
Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instruct	Jun 20, 2025	256K	$0.09	$0.25	-	tools open weights
Mistral Medium 3mistralai/mistral-medium-3	May 7, 2025	131K	$0.40	$2.00	9	tools
Mistral Small 3.1 24Bmistralai/mistral-small-3.1-24b-instruct	Mar 17, 2025	128K	$0.35	$0.56	-	tools open weights
Sabamistralai/mistral-saba	Feb 17, 2025	33K	$0.20	$0.60	7	tools
Mistral Small 3mistralai/mistral-small-24b-instruct-2501	Jan 30, 2025	33K	$0.05	$0.08	7	open weights
Mistral Large 2407mistralai/mistral-large-2407	Nov 19, 2024	131K	$2.00	$6.00	8	tools
Mistral Nemomistralai/mistral-nemo	Jul 19, 2024	131K	$0.03	$0.03	-	tools open weights
Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct	Apr 17, 2024	66K	$2.00	$6.00	6	tools open weights
Mistral Largemistralai/mistral-large	Feb 26, 2024	128K	$2.00	$6.00	6	tools

Frequently asked

What is the cheapest Mistral AI model?: Mistral Nemo at $0.03 per 1M input tokens and $0.03 per 1M output tokens (vendor list price).
Which Mistral AI model has the largest context window?: Mistral Large 4 accepts 1.0M tokens of context.
How do I route to Mistral AI models with OpenSmartRoute?: Declare a target in targets.yaml with metadata.model set to the catalogue id (for example mistralai/mistral-large-4-0); the router scores it against every other target on cost, quality, latency and your policies for each request.

Route Mistral AI with everything else

OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a Mistral AI flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.

Cost estimator Playground Full catalogue

One of many

Mistral AI answers when it is the best answer for the request - and only then.

The prices on this page are the vendor's own list prices. Behind the router they become one column in a scorecard: for every request the candidates from Mistral AI are weighed against every other vendor on cost, quality prior, latency and your policy, and the trace records why the winner won. Bring your own Mistral AI key or buy by the token here; the decision is the same.

Photo: RDNE Stock project

For the business

What it does for the vendor strategy.

One URL, every vendor
No vendor lock-in
Point your OpenAI-compatible client at one address; add, swap or retire providers in the catalogue without touching application code.
Every vendor side by side
89% less
Lower cost per request
On the 150-prompt benchmark the router spent 89% less than sending every prompt to the reference model, and the judged quality went up, not down.
Read the benchmark
Self-hosting is free
Open source, Apache-2.0
The router is a library, a sidecar or a control plane you can run yourself, so the exit is always open.
What is open

Will this lock us into another vendor?: No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.
How much can we save on our LLM bill?: On the public benchmark the router saved 89% against sending everything to the reference model. Import last month's provider bill on the bill page and the estimate is computed on your own traffic before you change a line of code.
How do we compare AI gateways and routers?: The compare pages score each product against the same documented capabilities and say when the review was done; the benchmark page shows measured cost and quality, including the cases the router lost.

Model

Released

Context

Input / 1M

Output / 1M

Intelligence

Capabilities

Mistral Large 4mistralai/mistral-large-4-0

Oct 6, 2026

1.0M

$1.36

$4.18

reasoning tools

Mistral Medium 3.5mistralai/mistral-medium-3-5

Apr 30, 2026

262K

$1.50

$7.50

reasoning tools

Mistral Small 4mistralai/mistral-small-2603

Mar 16, 2026

262K

$0.15

$0.60

reasoning tools open weights

Devstral 2 2512mistralai/devstral-2512

Dec 9, 2025

262K

$0.40

$2.00

tools open weights

Ministral 3 14B 2512mistralai/ministral-14b-2512

Dec 2, 2025

262K

$0.20

tools open weights

Ministral 3 8B 2512mistralai/ministral-8b-2512

Dec 2, 2025

262K

$0.15

tools open weights

Ministral 3 3B 2512mistralai/ministral-3b-2512

Dec 2, 2025

131K

$0.10

tools open weights

Mistral Large 3 2512mistralai/mistral-large-2512

Dec 1, 2025

262K

$0.50

$1.50

tools

Voxtral Small 24B 2507mistralai/voxtral-small-24b-2507

Oct 30, 2025

33K

$0.10

$0.30

tools open weights

Mistral Medium 3.1mistralai/mistral-medium-3.1

Aug 13, 2025

131K

$0.40

$2.00

tools

Codestral 2508mistralai/codestral-2508

Aug 1, 2025

256K

$0.30

$0.90

tools

Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instruct

Jun 20, 2025

256K

$0.09

$0.25

tools open weights

Mistral Medium 3mistralai/mistral-medium-3

May 7, 2025

131K

$0.40

$2.00

tools

Mistral Small 3.1 24Bmistralai/mistral-small-3.1-24b-instruct

Mar 17, 2025

128K

$0.35

$0.56

tools open weights

Sabamistralai/mistral-saba

Feb 17, 2025

33K

$0.20

$0.60

tools

Mistral Small 3mistralai/mistral-small-24b-instruct-2501

Jan 30, 2025

33K

$0.05

$0.08

open weights

Mistral Large 2407mistralai/mistral-large-2407

Nov 19, 2024

131K

$2.00

$6.00

tools

Mistral Nemomistralai/mistral-nemo

Jul 19, 2024

131K

$0.03

tools open weights

Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct

Apr 17, 2024

66K

$2.00

$6.00

tools open weights

Mistral Largemistralai/mistral-large

Feb 26, 2024

128K

$2.00

$6.00

tools

Frequently asked

What is the cheapest Mistral AI model?

Mistral Nemo at $0.03 per 1M input tokens and $0.03 per 1M output tokens (vendor list price).

Which Mistral AI model has the largest context window?

Mistral Large 4 accepts 1.0M tokens of context.

How do I route to Mistral AI models with OpenSmartRoute?

Declare a target in targets.yaml with metadata.model set to the catalogue id (for example mistralai/mistral-large-4-0); the router scores it against every other target on cost, quality, latency and your policies for each request.

Mistral AI answers when it is the best answer for the request - and only then.

Mistral AI models

Every Mistral AI model

Frequently asked

Route Mistral AI with everything else

Mistral AI answers when it is the best answer for the request - and only then.

What it does for the vendor strategy.

No vendor lock-in

Lower cost per request

Open source, Apache-2.0

Mistral AI models

Every Mistral AI model

Frequently asked

Route Mistral AI with everything else

Mistral AI answers when it is the best answer for the request - and only then.

What it does for the vendor strategy.

No vendor lock-in

Lower cost per request

Open source, Apache-2.0