LLM Reference

Mixtral 8x7B

Released
2023-12-11
Last refreshed
2026-06-29
Status
Researched 74d ago
Open sourceCommercial use: permittedCodingClassification

Mixtral 8x7B is worth evaluating for coding and classification when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding and classification
  • Workloads that can use a 32k context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads
  • Strict JSON or tool-calling flows
Specifications
Family
Mixtral
Released
2023-12-11
Context
32k
Parameters
8x7B
Architecture
Mixture of Experts
Knowledge cutoff
2023-12
Specialization
general
Openness
Open source
License
Apache 2.0OSI-approvedCommercial use: permitted
Training
Fine-tuned

About

Mixtral 8x7B, developed by Mistral AI, features a cutting-edge Mixture of Experts (MoE) architecture, utilizing eight experts with seven billion parameters each, yielding a total of 46.7 billion parameters. This architecture activates only two experts per token, allowing for efficient processing and a 6x faster inference rate compared to Llama 2 70B. The model excels in performance, surpassing Llama 2 70B and competing with GPT-3.5 on numerous benchmarks. It supports multiple languages and can handle context up to 32,000 tokens, enhancing understanding of lengthy text. Designed for diverse tasks, it is strong in code generation and available under a permissive Apache 2.0 license, promoting community engagement. Compatible with various optimization tools, its weights are easily deployable, with Mistral AI continuing to improve its capabilities through performance optimizations and fine-tuning efforts.

Mixtral 8x7B is an open-source model in the Mixtral family. The structured metadata tracks a 32k-token context window. This page tracks provider routes through Databricks Foundation Model Serving, NVIDIA NIM, GCP Vertex AI, and 15 more, with the cheapest tracked route listed at $0.15 input and $0.45 output per 1M tokens. Headline tracked benchmarks include Google-Proof Q&A 54.8, HellaSwag 90.9, and HumanEval 80.5.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ A

1 relevant benchmark in the decision map.

Classification

Q/$ B

2 relevant benchmarks in the decision map.

Provider price ladder

Compare all 18

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
SiliconFlow$0.200$0.200
Serverless
Microsoft Foundry$0.270$0.270
Provisioned
Lepton AI API$0.300$0.300
Serverless
Mistral AI Studio$0.150$0.450
Serverless

Available via routers & gateways(16)

LiteLLM

Gateway

Open-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.

Free OSSGCP Vertex AIMicrosoft FoundryMistral AI Studio

OpenRouter

Hybrid

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

PassthroughGCP Vertex AIMistral AI StudioFireworks AI

Portkey

Gateway

Production AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.

SubscriptionGCP Vertex AIMicrosoft FoundryMistral AI Studio

AIRouter

Router

Commercial LLM router that analyzes incoming requests and routes to the optimal model for cost/quality/latency via a drop-in OpenAI-compatible API, with a privacy-preserving embedding mode that avoids sending prompt content.

Passthrough + feeGCP Vertex AIMistral AI Studio

Amazon Bedrock Intelligent Prompt Routing

Router

AWS Bedrock's native intelligent prompt router that routes prompts between Anthropic Claude model tiers (Haiku/Sonnet) based on predicted task complexity, with no extra per-routing charge.

PassthroughAWS Bedrock

Azure AI Foundry Model Router

Router

Microsoft Azure AI Foundry's native model router that uses a trained ML model to route each prompt in real time to the optimal Azure-hosted model, with Balanced/Cost/Quality mode selection and automatic failover.

PassthroughMicrosoft Foundry

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Coding

Benchmark scores(4)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
Google-Proof Q&A54.8diamondhttps://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard
HellaSwag90.910-shothttps://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard
HumanEval80.5pass@1https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard
Massive Multitask Language Understanding80.25-shothttps://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard

Migration checks

No linked migration route is available for this model yet.

Compare Mixtral 8x7B with other models

Show all 39 popular comparisonssorted by 7-day search impressions

Frequently asked questions

What is the context window of Mixtral 8x7B?

Mixtral 8x7B has a context window of 32k tokens.

How much does Mixtral 8x7B cost?

Mixtral 8x7B pricing ranges from $0.15/1M to $0.6/1M input tokens depending on the provider.

When was Mixtral 8x7B released?

Mixtral 8x7B was released on 2023-12-11.

Which providers offer Mixtral 8x7B?

Mixtral 8x7B is available from 18 providers: Databricks Foundation Model Serving, NVIDIA NIM, GCP Vertex AI, AWS Bedrock, OctoAI API (Deprecated), Fireworks AI, Mistral AI Studio, Baseten API, Lepton AI API, Microsoft Foundry, Alibaba Cloud PAI-EAS, IBM watsonx, Scale AI GenAI Platform, DeepInfra, Bitdeer AI, SiliconFlow, Replicate API, Vultr.

What benchmarks has Mixtral 8x7B been tested on?

Mixtral 8x7B has been evaluated on 4 benchmarks, including Google-Proof Q&A, HellaSwag, HumanEval, Massive Multitask Language Understanding.