Eliminating the 4 Hidden Taxes: AI Tokens, Manual Work, SaaS Cliffs & AI Scrapers Sponsor this header →

Mistral: Mixtral 8x22B Instruct API Pricing & Cost Breakdown

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,...

mistralai/mixtral-8x22b-instruct
Open Weight
Last checked: Nov 21, 2026
Input / 1M Tokens
$2.00
Prompt & context tokens
Output / 1M Tokens
$6.00
Generated completion tokens
Blended (3:1) / 1M
$3.00
Tier: balanced
Context Window
66K
Max output: 52K

Technical Specifications

Canonical IDmistralai/mixtral-8x22b-instruct
ProviderMistral AI
Input Modalitiestext, file
Output Modalitiestext
Open-WeightYes
Reasoning OptimizedStandard
Vision SupportText-only

Estimated Monthly API Spend

StageMonthly TokensEst. Cost
Prototype / MVP
500 req/day
22.5M in / 6.0M out $81.00/mo
Growing SaaS
10,000 req/day
600.0M in / 150.0M out $2,100/mo
Scale Production
100,000 req/day
7500.0M in / 1800.0M out $25,800/mo
Simulate Custom Volume → Cut Cost via 3-Tier Cascade →

Deploy or Route Mistral: Mixtral 8x22B Instruct

Multi-Provider Gateway

OpenRouter

Unified API gateway for 300+ LLMs with automatic fallbacks and unified billing.

Call via OpenRouter →
Open-Weight Inference

Together AI

High-throughput serverless inference & fine-tuning for Llama, DeepSeek, and Qwen.

Run on Together AI →
Low-Latency Engine

Fireworks AI

Ultra-low-latency inference engine built for production structured outputs and function calling.

Deploy on Fireworks →

Some outbound infrastructure and API gateway links on KostoZero are partner referrals that help keep this observatory free and independent at no extra cost to you.

Cheaper Alternatives to Mistral: Mixtral 8x22B Instruct

ModelProviderInput / 1MOutput / 1MBlendedContext
Z.ai: GLM 5.3 Prime Z Ai $1.68 $5.28 $2.58 1M
Qwen: Qwen3.7 Max Qwen $1.48 $4.42 $2.21 1M
Z.ai: GLM 5.1 Z Ai $1.40 $4.40 $2.15 205K
DeepSeek: DeepSeek Pro Latest DeepSeek $0.10 $8.00 $2.07 1.05M
DeepSeek: DeepSeek V4 Pro 0813 DeepSeek $1.32 $3.96 $1.98 1.05M
Writer: Palmyra X5 Writer $0.60 $6.00 $1.95 1.04M

Frequently Asked Questions

How much does Mistral: Mixtral 8x22B Instruct API cost per 1M tokens?

Mistral: Mixtral 8x22B Instruct costs $2.00 per 1M input tokens and $6.00 per 1M output tokens ($3.00 blended at a 3:1 ratio).

What is the maximum context window of Mistral: Mixtral 8x22B Instruct?

Mistral: Mixtral 8x22B Instruct supports up to 65,536 tokens (66K) of input context and up to 52,428 output completion tokens.

What are cheaper alternatives to Mistral: Mixtral 8x22B Instruct?

Lower-cost options tracked right now include Z.ai: GLM 5.3 Prime ($2.58/1M), Qwen: Qwen3.7 Max ($2.21/1M), Z.ai: GLM 5.1 ($2.15/1M).

Get Instant Price-Drop (>10%), New AI Bot & SaaS Cliff Alerts

Every 6 hours our autonomous sync checks 40+ LLMs, AI crawlers, and SaaS pricing cliffs—alerting you when prices drop >10% or new scrapers appear.