Mistral NeMo — Mistral AI | Modeldex

Mistral NeMo

Active

12B open-weights model built with NVIDIA, with 128k context.

Updated 3 days agoStructured data from Modeldex catalog

AgenticOpen source

Knowledge cutoff

Apr 30, 2024(2.0 years ago)

API release

Jul 19, 2024(1.8 years ago)

Not enough benchmark coverage yet for an Intelligence Index — needs at least 3 results across 2 categories.

Overview

Mistral NeMo is a 12B parameter model developed in partnership with NVIDIA, featuring a 128k context window and Tekken tokenizer. Apache-2.0 licensed.

History

Mistral NeMo became available via the Mistral AI API on 2024-07-19.

Training & availability

Training data has a knowledge cutoff of 2024-04-30 — information about events after that date is unlikely to appear in the model's responses. Weights are publicly available under the Apache-2.0 license, making this an open-weight model suitable for on-prem deployment and fine-tuning.

Capabilities

Context window: 128K tokens.
Max output: 8K tokens.
Input modalities: text.

Recommended for: agentic, open-source.

Limitations

The knowledge cutoff is 23 months old — this model will not know about recent events, releases, or API changes.
Text-only — cannot process images, audio, or video inputs.

Quick start

Minimal example using the OpenRouter API. Copy, paste, replace the key.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="sk-or-...",
)
resp = client.chat.completions.create(
    model="mistral/mistral-nemo",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)

Cost calculator

Estimate your monthly bill. Presets are typical workload sizes.

Input tokens / month5.0M

@ $0.15/1M

Output tokens / month2.0M

@ $0.15/1M

Input cost

$0.75

5.0M × $0.15/1M

Output cost

$0.3

2.0M × $0.15/1M

Total / month

$1.05

$12.6 / year

Providers & performance

3 providers

Multi-provider inference routes for this model — sorted by throughput. Latency is time-to-first-token; throughput is output tokens per second. Data from OpenRouter, measured over the last 30 minutes.

Provider	Throughput	Latency (TTFT)	Input $ / 1M	Output $ / 1M	Context	Quant	Supports
Mistral	83tok/s	296ms	$0.15	$0.15	131K	—	tools · json
DeepInfra	36tok/s	287ms	$0.02	$0.04	131K	fp8	json
Novita	19tok/s

Popularity

Signals from open-source communities — not a quality measure, but useful for gauging adoption among developers.

🤗

HuggingFace downloads

134.2K/ month

HuggingFace likes

1.7K

Integrations & tooling support

Tool calling: Supported
Structured outputs: Not supported

Price vs quality

Budget pricing

Priced low — good for high-volume tasks. Quality tier pending more benchmark coverage.