mistralai
Mistral: Mixtral 8x22B Instruct
mistralai/mixtral-8x22b-instruct
Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...
- Type
- text
- Provider
- mistralai
- Model ID
- mistralai/mixtral-8x22b-instruct
- Capabilities
- tools
- Context window
- 66K tokens
- Self-hostable
- Yes — runs on your own GPU
- Input price
- $2.20 / 1M tokens
- Output price
- $6.60 / 1M tokens
Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.
What it costs to run
cloud · 1M in + 1M out
$8.80
$2.20 for a million input tokens plus $6.60 for a million output tokens, billed from credits only when a request fails over to the cloud.
your hardware
$0 / token
Served from a workstation or on-prem server you own, there is no per-token fee — the marginal cost is power.
Run it on your own hardware
Estimated GPU memory for Mistral: Mixtral 8x22B Instruct (176B parameters), for the weights alone — add room for the context cache.
- Q4_K_M
- ~100.7 GBmulti-GPU or large unified memory
- Q8_0
- ~174.5 GBmulti-GPU or large unified memory
- FP16 / BF16
- ~328.6 GBmulti-GPU or large unified memory
Install the agent on the machine and it dials out to the gateway over a single WebSocket — no port forwarding or inbound firewall rules. Requests for this model go to your node first and fail over to the cloud only when it can't serve.
/// initialize
Call Mistral: Mixtral 8x22B Instruct through one OpenAI-compatible endpoint.
Serve it from hardware you own, with cloud failover when your nodes are busy or offline.
no credit card · 2 nodes free · openai-compatible
Frequently asked questions
- What is the context window of Mistral: Mixtral 8x22B Instruct?
- Mistral: Mixtral 8x22B Instruct accepts up to 65,536 tokens (66K) of context per request.
- How much does Mistral: Mixtral 8x22B Instruct cost per million tokens?
- Through Wide Area Intelligence, Mistral: Mixtral 8x22B Instruct costs $2.20 per 1M input tokens and $6.60 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $8.80.
- Can I run Mistral: Mixtral 8x22B Instruct on my own hardware?
- Yes — Mistral: Mixtral 8x22B Instruct is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 100.7 GB of GPU memory, plus room for the context cache — more than a single 80 GB card, so plan for multiple GPUs or a large unified-memory machine. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.
More from mistralai
- Mistral Largemistralai/mistral-large
- Mistral Large 2407mistralai/mistral-large-2407
- Mistral: Codestral 2508mistralai/codestral-2508
- Mistral: Devstral 2 2512mistralai/devstral-2512
- Mistral: Ministral 3 14B 2512mistralai/ministral-14b-2512
- Mistral: Ministral 3 3B 2512mistralai/ministral-3b-2512
- Mistral: Ministral 3 8B 2512mistralai/ministral-8b-2512
- Mistral: Mistral Large 3 2512mistralai/mistral-large-2512