Mistral: Mixtral 8x22B Instruct

MISTRALAI Developer Architecture Profile

OpenRouter ↗HuggingFace ↗

Intelligence (ELO)1442Chatbot Arena Verified

Max Context Limit65,536Max Out: 52,428 tokens

Prompt Caching90% OFF$0.20 / 1M cached

Standard API / 1M$8.00Blended Standard Rate

Model Capabilities & Contract SLAs

Classification
Conversational
Agentic
Coding & Logic
Fictional
📋 Strict JSON Schema
🛠️ Native Tool Calling

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,...

Granular Pricing Matrix

Input Tokens (Standard Prompt)$2.00 / 1M

⚡ Cached Input (Prompt Cache Read)90% OFF$0.20 / 1M

Output Tokens (Completion)$6.00 / 1M

Pricing data via OpenRouter. Sync: 10/2/2026

Evaluate Competitors

VS Engine MatchupMistral: Mixtral 8x22B Instruct vs Apodex: Apodex 1.1 Mini (free)VS Engine MatchupMistral: Mixtral 8x22B Instruct vs Z.ai: GLM 5V Turbo VS Engine MatchupMistral: Mixtral 8x22B Instruct vs ByteDance Seed: Seed-2.0-Mini VS Engine MatchupMistral: Mixtral 8x22B Instruct vs Qwen: Qwen3.5-122B-A10B VS Engine MatchupMistral: Mixtral 8x22B Instruct vs Mistral: Devstral 2 2512 VS Engine MatchupMistral: Mixtral 8x22B Instruct vs Relace: Relace Search