Mixtral 8x22B Instruct
4658°
Run this model
Offers / Ads
Mistral | 65,536 token context | $2.00/M input, $6.00/M output. Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: See benchmarks on the launch announcement hereOpens in new tab. #moe
Guides for this model
Best local LLM by use case (October 2026): the right open model for every job
How much VRAM do I actually need for local AI?
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
Captain's notes
Notes from 2026-10-13
Mixtral 8x22B Instruct is Mistral's instruction-tuned sparse mixture-of-experts model, activating 39B parameters at inference time from a 141B total. The MoE architecture means you get capability closer to a large dense model at a fraction of the compute cost. It suits developers who need strong general performance and want open weights they can self-host or run via API.
Known for
- Sparse MoE design: 39B active parameters from 141B total keeps inference costs down.
- Open weights available on Hugging Face for self-hosting.
- Native function-calling support built into the tokenizer.
- Compatible with both mistral_inference and Hugging Face transformers pipelines.
Watch out for
- 141B total parameters means serious VRAM requirements for local inference; quantization is almost mandatory.
- Mistral recommends mistral_common tokenizer for exact results; the HF tokenizer may diverge slightly.
- At $6.00/M output tokens via API, costs climb fast on long generative tasks.
Prompts to try
Multi-step function plan
You have two tools: search_web(query) and send_email(to, subject, body). A user asks: 'Find the current price of copper futures and email a summary to procurement@example.com.' Write out the exact sequence of tool calls you would make, with arguments, and explain your reasoning between each step.
Refactor for readability
Refactor the following Python function so it is easier to read and maintain. Add type hints, rename any unclear variables, and split it if it does more than one thing. Explain each change you made and why.
def proc(d, x):
r = []
for i in d:
if i['v'] > x:
r.append({'id': i['id'], 'val': i['v'] * 1.1})
return r
Structured data extraction
Extract every company name, founding year, and headquarters city from the text below. Return the result as a JSON array where each object has keys 'company', 'founded', and 'city'. If a field is not mentioned, use null.
'Stripe was founded in 2010 and is based in San Francisco. Revolut, headquartered in London, launched in 2015. Adyen has operated from Amsterdam since 2006.'
Compare with
- Mistral Large 4API-only model1,048,576 token context · $0.68/M input, $2.09/M output
- Mistral LargeAPI-only model128,000 token context · $2.00/M input, $6.00/M output
- Mistral Medium 3.5API-only model262,144 token context · $1.50/M input, $7.50/M output
- Mistral Medium 3API-only model131,072 token context · $0.40/M input, $2.00/M output
More text models from mistralai
Questions people ask
- Can I run Mixtral 8x22B Instruct locally?
- Yes, the weights are open and hosted at mistralai/Mixtral-8x22B-Instruct-v0.1 on Hugging Face. Bear in mind the full model is 141B parameters, so you will almost certainly need quantization to fit it into consumer or prosumer hardware.
- What does it cost and what is the context window?
- Via API the model is priced at $2.00 per million input tokens and $6.00 per million output tokens, with a 65,536-token context window.
- How does the 8x22B differ from Mixtral 8x7B?
- The 8x22B scales up both the number of experts and their size, activating 39B parameters per forward pass versus roughly 12B in the 8x7B, which translates to stronger performance at the cost of higher VRAM and slightly higher API pricing.
Captain's verdictA capable open-weights workhorse with a clever cost-per-token story, though local deployment demands serious hardware planning.
Model card on Hugging Face
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
How this score adds up
This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
Mixtral 8x22B Instruct is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153