What is the Tekken tokenizer?

Tekken is a tokenizer trained on 100+ languages, introduced with Mistral Nemo. Tekken achieves ~30% better source code compression, 2x better compression for Korean, and 3x better compression for Arabic compared to previous Mistral tokenizers.

Is Mistral Nemo a drop-in replacement for Mistral 7B?

Yes. Mistral positions it as a drop-in upgrade with the same architecture family, improved quality, and a larger context window.

What is FP8 inference and how does quantization-aware training help?

FP8 is a reduced-precision number format that speeds inference and reduces memory usage. Quantization-aware training means the model was trained to tolerate FP8 quantization, so accuracy doesn't degrade compared to full-precision inference.

What is the license for Mistral Nemo?

Apache 2.0, permitting commercial use and modification.

Who built Mistral Nemo?

Mistral in collaboration with NVIDIA, as indicated by the NeMo branding aligned with NVIDIA's NeMo framework ecosystem.

Mistral

Mistral Nemo

Mistral Nemo is a 12B model with a context window of 131.1K tokens and the Tekken tokenizer trained on 100+ languages, offering ~30% better source code compression and improved multilingual efficiency as a drop-in replacement for Mistral 7B.

View API reference

Input and output price: Prices from: Input $0.02, Output $0.04, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { streamText } from 'ai'

const result = streamText({
  model: 'mistral/mistral-nemo',
  prompt: 'Why is the sky blue?'
})

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out Mistral Nemo 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 Nemo

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

Novita AI

Legal:Terms•Privacy

60K

16K

2.4 s

32 tps

$0.04/M

$0.17/M

—

07/18/2024

Mistral

Legal:Terms•Privacy

128K

0.3 s

104 tps

$0.15/M

—

07/18/2024

DeepInfra

Legal:Terms•Privacy

131K

0.3 s

25 tps

$0.02/M

$0.04/M

—

07/18/2024

Getting started

Call Mistral Nemo 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/mistral-nemo',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same Mistral Nemo 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/mistral-nemo',
    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.

Parameter	Type	Required	Description
`model`	`string`	Yes	Model ID in the form `creator/model`, e.g. `mistral/mistral-nemo`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. Mistral Nemo supports up to `131,072` output tokens.
`providerOptions`	`Record<string, JSONValue>`	No	AI Gateway routing options under `gateway`, plus any provider-native options under the provider’s own namespace — see the table below.

Input limits

Input	Formats	Sources	Max count	Max size	Limits
Text	—	—	—	—	Prompt and response share the 131K-token context window

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/mistral-nemo',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['novita', '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.

Parameter	Type	Required	Description
`providerOptions.gateway.only`	`string[]`	No	Restrict routing to these provider slugs. Requests fail over only within the listed providers.
`providerOptions.gateway.order`	`string[]`	No	Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks.
`providerOptions.gateway.sort`	`'cost' \| 'ttft' \| 'tps'`	No	Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order.
`providerOptions.gateway.zeroDataRetention`	`boolean`	No	Route 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.

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/mistral-nemo',
    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

mistral/mistral-large-3

256K

0.5 s

80 tps

$0.50/M

$1.50/M

—

12/02/2025

mistral/ministral-14b

256K

0.3 s

113 tps

$0.20/M

—

12/02/2025

mistral/codestral-embed

—

$0.15/M

—

05/28/2025

mistral/ministral-3b

128K

0.3 s

253 tps

$0.10/M

—

10/16/2024

mistral/mistral-small

32K

0.3 s

28 tps

$0.10/M

$0.30/M

—

09/17/2024

mistral/mistral-embed

—

$0.10/M

—

12/11/2023

Copy link to headingAbout Mistral Nemo

Released July 18, 2024, Mistral Nemo was built in collaboration with NVIDIA and introduced the Tekken tokenizer, trained across 100+ languages, as its defining technical innovation. Tekken achieves ~30% better compression for source code compared to previous Mistral tokenizers, 2x better compression for Korean, and 3x better compression for Arabic. These compression gains directly reduce token consumption and cost.

At 12B parameters with a context window of 131.1K tokens, Mistral Nemo serves as a drop-in replacement for Mistral 7B. Mistral Nemo provides enhanced instruction following, multi-turn conversation quality, and code generation. Quantization-aware training enables FP8 inference without performance degradation. The combination of quantization awareness and Tekken compression gives Mistral Nemo deployment efficiency advantages.

Mistral Nemo's multilingual coverage spans English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi. Mistral Nemo is available under Apache 2.0, with both base and instruct weights on HuggingFace.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: The Tekken tokenizer's compression efficiency means that for code-heavy or non-Latin-script workloads, you use fewer tokens per request than with models using conventional tokenizers.
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 Mistral Nemo

Best for

Multilingual applications: Spanning European, East Asian, and Arabic-script languages
Code-heavy workloads: Tekken's 30% compression advantage reduces token costs
Korean or Arabic applications: 2-3x tokenizer compression is significant
Mistral 7B migrations: Deployments that need a larger context window

Consider alternatives when

Larger general-purpose headroom: You need more capacity (consider Mistral Large 3)
Code generation or agentic coding: Coding is the primary task (consider Devstral or Codestral)
Higher reasoning depth: Tasks that require deeper reasoning traces (consider Magistral models)

Copy link to headingConclusion

Mistral Nemo's Tekken tokenizer is its distinguishing technical contribution, delivering efficiency gains for code and non-Latin-script languages that translate into lower costs per task. For multilingual applications and code-heavy pipelines, those gains compound at scale.

Copy link to headingFrequently Asked Questions

What is the Tekken tokenizer?
Tekken is a tokenizer trained on 100+ languages, introduced with Mistral Nemo. Tekken achieves ~30% better source code compression, 2x better compression for Korean, and 3x better compression for Arabic compared to previous Mistral tokenizers.
What is the context window for Mistral Nemo?
131.1K tokens.
Is Mistral Nemo a drop-in replacement for Mistral 7B?
Yes. Mistral positions it as a drop-in upgrade with the same architecture family, improved quality, and a larger context window.
What languages does Mistral Nemo support?
English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi, among others.
What is FP8 inference and how does quantization-aware training help?
FP8 is a reduced-precision number format that speeds inference and reduces memory usage. Quantization-aware training means the model was trained to tolerate FP8 quantization, so accuracy doesn't degrade compared to full-precision inference.
What is the license for Mistral Nemo?
Apache 2.0, permitting commercial use and modification.
Who built Mistral Nemo?
Mistral in collaboration with NVIDIA, as indicated by the NeMo branding aligned with NVIDIA's NeMo framework ecosystem.

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

Agent Stack

Core Platform

Tools

Learn

Build

Explore

Mistral Nemo

Copy link to headingPlayground

Copy link to headingProviders

Copy link to headingUptime24 hours

Copy link to headingThroughput24 hours

Copy link to headingLatency24 hours

Getting started

Top-level parameters

Input limits

Provider options

Routing across providers

Tool calling

Copy link to headingMore models by Mistral

Copy link to headingAbout Mistral Nemo

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use Mistral Nemo

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions