Mixtral 8x22B Instruct
Mistral AI · released Apr 16, 2024 · mistralai/Mixtral-8x22B-Instruct-v0.1
- Type
- Open weightsApache License 2.0
- Params
- 141B
- Context
- 66K
39B active per word · about 49K words of context
Our take
Written Sep 2, 2026Mixtral 8x22B Instruct is Mistral AI's largest downloadable model, a sparse mixture-of-experts with 141 billion total parameters and 39 billion active per token. Released in 2024 under an Apache 2.0 licence, it handles up to 65,536 tokens in a single request and accepts file attachments alongside text.
Pick this for self-hosted or local deployment where a permissive licence matters, or for long-context work up to 65,536 tokens. It suits budget-conscious API access when throughput is not critical. Skip it if you need graduate-level reasoning accuracy, frontier-level chat or coding quality, or meaningful price competition between providers.
The case for it
- Apache 2.0 licence allows commercial use, fine-tuning and redistribution without restriction.
- 65,536-token request limit is large for a 2024 open-weights model.
- Strong instruction-following on rubric-based benchmarks, at 71.8% on IFEval.
- Higher measured throughput on Mistral's own hosting at the base price: 49.5 tps versus 19 tps on the pricier tier.
The case against it
- Weak on graduate-level reasoning and broad knowledge: 16.4% on GPQA Diamond and 38.7% on MMLU-Pro.
- Mid-table Arena scores on every measured dimension, with coding as its relative high point yet still behind current frontier.
- Only three tracked offers and no real price competition; two providers charge the same rate.
How good is it?
An open-weights text model for chat and general requests, though it trails the field on everyday questions, writing and coding.
- getting answers to everyday questionsArena Text (overall) · 164th of 168
- drafts, rewrites and editingArena Creative Writing · 165th of 168
- writing and completing codeArena Coding · 162nd of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)164th of 168 · 1230
CodingWriting and fixing code on its own
Arena Coding162nd of 168 · 1278
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing165th of 168 · 1191
Arena Creative Writing is the only board that has scored it for this.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model9 scoresEvery figure we hold, from 9 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Ultra (64-core GPU) · 128 GB
Borderline fit on an estimated size. It leaves 3 GB spare on a size we calculated rather than measured, and a 10% error either way would change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $2.00 in / $6.00 out
- Context served
- 66K
- Throughput
- ~82 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $2.00 / $6.00checked 4 hours ago | 66K | not measured | Unknown | Unknown | Unknown |
| Mistral AIThrough OpenRouter | $2.00 / $6.00checked 4 hours ago | 66K52K max reply | 82 tok/s | No | Yes30 days | Confirmed |
| Mistral AIeuThrough OpenRouter | $2.20 / $6.60checked 4 hours ago | 66K52K max reply | 26 tok/s | No | Yes30 days | Confirmed |
OpenRouterAcross the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 does not say. 2 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Mistral AIThrough OpenRouter | ✓ | ✓ | ✓ |
| Mistral AIeuThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 3 of 3 listings say yes. JSON output: 3 of 3 listings say yes. Strict schema: 3 of 3 listings say yes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- mistralai/Mixtral-8x22B-Instruct-v0.1
- Architecture
- Mixture of experts
- Takes in, gives back
- Text and documents in, text out
- Catalogue slug
- mistralai-mixtral-8x22b-instruct