Skip to content
Dashboard

Ministral 14B

Ministral 14B is part of Mistral's third-generation edge series, achieving 85% on AIME '25 with its reasoning variant and supporting native image understanding for on-device and edge deployment.

View API reference
Input and output price
Input $0.20, Output $0.20, Per 1M tokens
24h uptime
Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({
model: 'mistral/ministral-14b',
prompt: 'Why is the sky blue?'
})
Read docs

Copy link to headingPlayground

Try out Ministral 14B by Mistral. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

mistral logo
mistral logo

Ministral 14B

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider
Context
Max Output
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
ZDR
No Training
Free Tier
Release Date
256K256K0.3 s113 tps
$0.20/M
$0.20/M
12/02/2025

Copy link to headingUptime

Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.

Copy link to headingThroughput

P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.

Copy link to headingLatency

P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.

Getting started

Call Ministral 14B through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.

index.ts
import { generateText } from 'ai';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'mistral/ministral-14b',
prompt: 'Why is the sky blue?',
});
console.log(result.text);
}
main().catch(console.error);

Top-level parameters

The same Ministral 14B request in each API format AI Gateway supports.

top-level-params.ts
import { generateText } from 'ai';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'mistral/ministral-14b',
system: 'You are a concise technical assistant.',
prompt: 'Summarize the tradeoffs between static generation and SSR.',
maxOutputTokens: 1024,
temperature: 0.5,
});
console.log(result.text);
}
main().catch(console.error);

Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. mistral/ministral-14b. AI Gateway routes the request to an available provider.
maxOutputTokensnumberNoHard cap on generated tokens. Ministral 14B supports up to 256,000 output tokens.
providerOptionsRecord<string, JSONValue>NoAI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below.

Input limits

InputFormatsSourcesMax countMax sizeLimits
TextPrompt and response share the 256K-token context window
ImageURL, base64, Uint8ArraySent as image parts in messages; counts as input tokens
PDFURL, base64, Uint8ArraySent as file parts in messages; counts as input tokens

Provider options

Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.

Learn more in the AI SDK mistral provider docs.

provider-options.ts
import { generateText } from 'ai';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'mistral/ministral-14b',
prompt: 'Why is the sky blue?',
providerOptions: {
gateway: {
only: ['mistral'],
},
},
});
console.log(result.text);
}
main().catch(console.error);

These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.

ParameterTypeRequiredDescription
providerOptions.gateway.onlystring[]NoRestrict routing to these provider slugs. Requests fail over only within the listed providers.
providerOptions.gateway.orderstring[]NoPreferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks.
providerOptions.gateway.sort'cost' | 'ttft' | 'tps'NoRank candidate providers by price, time to first token, or tokens per second instead of the default routing order.
providerOptions.gateway.zeroDataRetentionbooleanNoRoute only to providers with a zero-data-retention policy for this model.

Routing across providers

AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.

Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.

Image input

Send images alongside text as message parts. Images count as input tokens.

image-input.ts
import { generateText } from 'ai';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'mistral/ministral-14b',
messages: [
{
role: 'user',
content: [
{ type: 'text', text: 'Describe this image.' },
{ type: 'image', image: 'https://example.com/photo.jpg' },
],
},
],
});
console.log(result.text);
}
main().catch(console.error);

PDF input

Attach PDFs as file parts. Their contents count as input tokens.

pdf-input.ts
import { generateText } from 'ai';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'mistral/ministral-14b',
messages: [
{
role: 'user',
content: [
{ type: 'text', text: 'Summarize this document.' },
{
type: 'file',
mediaType: 'application/pdf',
data: 'https://example.com/document.pdf',
},
],
},
],
});
console.log(result.text);
}
main().catch(console.error);

Tool calling

Expose tools the model can call. Define each tool’s inputs with a Zod schema.

tool-calling.ts
import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'mistral/ministral-14b',
prompt: 'What is the weather in San Francisco?',
tools: {
getWeather: tool({
description: 'Get the current weather for a location',
inputSchema: z.object({ location: z.string() }),
execute: async ({ location }) => ({ location, temperatureC: 18 }),
}),
},
});
console.log(result.text);
}
main().catch(console.error);

Copy link to headingMore models by Mistral

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Free Tier
Release Date
256K0.3 s
$1.50/M
$7.50/M
mistral logo
04/29/2026
256K0.5 s81 tps
$0.50/M
$1.50/M
mistral logo
12/02/2025
$0.15/M
mistral logo
05/28/2025
128K0.3 s253 tps
$0.10/M
$0.10/M
mistral logo
10/16/2024
32K0.3 s28 tps
$0.10/M
$0.30/M
mistral logo
09/17/2024
$0.10/M
mistral logo
12/11/2023

Copy link to headingAbout Ministral 14B

Ministral 14B is the 14B offering in Mistral's third-generation Ministral 3 series. Ministral 14B ships in base, instruct, and reasoning variants. The reasoning variant reaches 85% on AIME '25 in Mistral's Ministral 3 announcement.

All Ministral 14B variants include native image understanding, making Ministral 14B multimodal without requiring separate vision components. This is a key differentiator from the earlier Ministral series, which was text-only. Ministral 14B supports 40+ native languages for global deployments.

Mistral designed the Ministral 3 series for deployment spanning edge devices to enterprise workflows. All variants ship under Apache 2.0.

Copy link to headingWhat To Consider When Choosing a Provider

  • Configuration: Ministral 14B ships in base, instruct, and reasoning variants, all with native image understanding. The reasoning variant reaches 85% on AIME '25 in Mistral's published Ministral 3 post.
  • Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
  • Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use Ministral 14B

Best for

  • Unified text and image applications: Combine generation and vision in a single model
  • Extended thinking capability: Use cases that benefit from the reasoning variant
  • Multilingual applications: Serving diverse global regions
  • Apache 2.0 for commercial products: Teams that need an Apache 2.0 license

Consider alternatives when

  • Smaller parameter footprint: You need a more compact model (consider Ministral 3B or 8B)
  • Server-side throughput at scale: Peak server throughput is the primary concern

Ministral 14B is an edge-optimized model in Mistral's portfolio. Ministral 14B is multimodal from launch, optionally extended with reasoning, and designed for deployment from edge devices to enterprise workflows. Choose Ministral 14B when an application needs both image and text understanding at the 14B size class.

Copy link to headingFrequently Asked Questions

  • What is Ministral 14B's reasoning variant performance?

    85% on AIME '25 for the reasoning variant, per Mistral's Ministral 3 announcement.

  • Does Ministral 14B support image inputs?

    Yes. Native image understanding is included in all variants (base, instruct, and reasoning) as part of the Ministral 3 series.

  • What deployment targets does Ministral 14B cover?

    Mistral designed the Ministral 3 series for deployment from edge devices to enterprise workflows.

  • What license covers Ministral 14B?

    Apache 2.0.

  • Is Ministral 14B multilingual?

    Yes. The Ministral 3 series supports 40+ native languages.

  • How does the reasoning variant differ from the instruct variant?

    The reasoning variant activates extended thinking to improve accuracy on complex problems. The instruct variant is optimized for standard instruction-following tasks with lower latency.

  • How does Ministral 14B compare to Ministral 8B?

    Ministral 14B adds image understanding, reasoning capability, and higher benchmark performance. Ministral 8B is text-only but features a specialized interleaved sliding-window attention pattern for faster and more memory-efficient inference at lower cost.

Your use is subject to Mistral's Terms & Privacy Policies.