Skip to content
RankShark

Mistral Nemo

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.

ModelOpen sourceby Mistralsince 2024
29.3

SharkScore

#230 in Models

Why it scores 29.3

Mistral Nemo has a SharkScore of 29.3/100, ranked #230 of 607 in Models (updated 2026-11-19).

Each part compares Mistral Nemo with other listings in Models. Evidence covers 87% of the score's weight.

Adoption
16 · 30%
User reviews
no data · 25%
Maintenance
1 · 20%
Trust & transparency
80 · 15%
Momentum
no data · 10%

Paying never changes this score. How ranking works · method v2026-11-18.2

RankShark review of Mistral Nemo

Automated evaluation by RankShark · 18 Nov 2026 · method v1.0 · How we review

We were not paid for this review.

As of 2026-11-18, Mistral Nemo is a 12B text model with a 131,072-token OpenRouter context listing and per-token pricing. [E2, MEASURED]

Mistral Nemo is a text-generation model built by Mistral with NVIDIA. Its instruct version is available on Hugging Face, and OpenRouter lists it for API inference. [E1, E2]

Best for

  • Developers looking for a model listing with a long context window. · OpenRouter
  • Teams working with the listed multilingual languages or code. · model card
  • Developers who want to run the model using supported inference or model frameworks. · model card

Not for

  • Deployments that require moderation mechanisms built into the model; the model card says it does not have them. · model card

Key features

  • Context length. The vendor model card says it was trained with a 128k context window; OpenRouter lists 131,072 tokens. [E1, E2] · model card, OpenRouter
  • Multilingual and code training. The vendor says it was trained on a large proportion of multilingual and code data. [E1] · model card
  • Tool calling. The vendor provides function-calling examples for mistral-inference and Transformers. [E1] · model card
  • Model access. The vendor documents use with mistral-inference, Transformers, and NVIDIA NeMo. [E1] · model card
  • OpenRouter API parameters. OpenRouter lists parameters including tools, temperature, response_format, and max_tokens. [E2] · OpenRouter

Pros

  • The model card lists the Apache 2 License. · model card
  • The vendor documents tool-calling examples for two frameworks. · model card
  • The model card lists support for multiple languages and says it was trained on multilingual and code data. · model card

Cons

  • The vendor says the instruct model has no moderation mechanisms. · model card
  • No free plan or free trial stated on the pages we checked.
  • Whether customer data is used for model training is not stated on the pages we checked.

Pricing

PlanPriceLimits
OpenRouter$0.029 per million input tokens; $0.03 per million output tokensOpenRouter lists a 131,072-token context length and a 16,384-token maximum completion length.

Checked 18 Nov 2026

Free plan
Not stated (checked 18 Nov 2026)
Free trial
Not stated (checked 18 Nov 2026)
Trains on customer data
Not stated (checked 18 Nov 2026)
Data retention
Not stated (checked 18 Nov 2026)
Data regions
Not stated (checked 18 Nov 2026)
Data processing agreement
Not stated (checked 18 Nov 2026)
AI models used
Mistral Nemo; the Hugging Face model card identifies the instruct version as Mistral-Nemo-Instruct-2407. · model card, OpenRouter
API
OpenRouter lists chat completions, completions, messages, and responses endpoints for the model. · OpenRouter
SDKs
The vendor documents use with mistral-inference, Hugging Face Transformers, and NVIDIA NeMo. · model card
Webhooks
Not stated (checked 18 Nov 2026)
Platforms
Hugging Face model files and local framework usage are documented by the vendor; OpenRouter lists API inference. · model card, OpenRouter
Security claims
No security certification stated (checked 18 Nov 2026)

What we measured

Context window (OpenRouter listing) · now
131,072 tokens
Price per million tokens (OpenRouter listing) · now
$0.029 in, $0.03 out
Package downloads · 30 days
91,107
How we tested · sources
  • Hourly uptime and response-time checks of the product's URL.
  • Repository, release and download data from GitHub, npm, PyPI and Hugging Face where they exist.
  • We did not sign up, pay, or use the product as a customer.
  • 18 Nov 2026: Plans or prices changed on the pricing page.
  • 18 Nov 2026: Plans or prices changed on the pricing page.

Something wrong? Report an error with a public link that shows it; corrections re-run the review.

Top alternatives to Mistral Nemo

See all
  • 67.1

    Qwen3.8 27B is an open-weight dense vision-language model from Qwen.

    ModelOpen source
  • 65.5

    Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per t

    ModelOpen source
  • 64.7

    Qwen3.8 Flash is a multimodal reasoning model from Alibaba.

    ModelOpen source
  • 64.3

    Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.

    ModelOpen source