Modeldex
Drag to turnCard front showing

MistralTextUncommonRetired

Mixtral 8x22B

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

open-mixtral-8x22b
Type
Text
Quality
30 · Top 70% on the Epoch Capabilities Index
Context window
64,000 tokens
Max output
64,000 tokens
Input price
$2.00 / 1M tokens
Output price
$6.00 / 1M tokens
Cache read
—
Cache write
—
Released
Apr 17, 2024
Knowledge cutoff
Apr 2024
Takes in
Text
Puts out
Text
Reasoning
No
Tool calling
Yes
Structured output
No
File attachments
No
Access
Open weights
License
Apache 2.0
Rarity
Uncommon
Set number
307/1040
Open Mistral docsQuality 30Where to run it 7Meet its creatureBattle Grok 4.7

No matching Hugging Face repo was found, so this shows Mistral’s usual open-weight license. Check the model card before relying on it. Specs from models.dev, last changed Oct 18, 2026. Official source: docs.mistral.ai.

How good is it?

Public leaderboard scores for Mixtral 8x22B, refreshed daily from Epoch AI and LMArena.

Top 70% of the 277 models on the Epoch Capabilities Index: #194.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Benchmarks Epoch AI runs

Scores from Epoch AI, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

7 providers sell Mixtral 8x22B through an API. Prices are per million tokens, cheapest first.

API providers

ProviderInputOutputContext
NvidiaFreemistralai/mixtral-8x22b-instructFreeFree66K
Kilo GatewayCheapest paidmistralai/mixtral-8x22b-instruct$2.00$6.0066K
MistralOfficialopen-mixtral-8x22b$2.00$6.0064K
NanoGPTmistralai/mixtral-8x22b-instruct-v0.1$2.00$6.0066K
OpenRoutermistralai/mixtral-8x22b-instruct$2.00$6.0066K
Prime Inferencemistralai/mixtral-8x22b-instruct$2.20$6.6066K
AI/ML APImistralai/mixtral-8x22b-instruct$2.75$8.2566K

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.

More from Mistral

Mistral

Mistral Large 4

CTX1.05M
NewBeta
75Quality
Reasoning · Vision · Tools
TextImageInput$0.68/M
TextOutput$2.09/M

Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work

PaidProprietary1028/1040
Mistral

Mistral Medium 3.5

CTX262K
59Quality
Reasoning · Vision · Tools
TextImageInput$1.50/M
TextOutput$7.50/M

Balanced Mistral model for enterprise assistants, multilingual work, and tools

Open weightsApache 2.0897/1040
Mistral

Mistral Small 4

CTX262K
Reasoning · Vision · Tools
TextImageInput$0.15/M
TextOutput$0.60/M

Fast Mistral production model for chat, extraction, and cost-sensitive agents

Open weightsApache 2.0829/1040
Mistral

Voxtral-Mini-4B-Realtime-2602

SIZE4.4B
Speech to text
AudioDownloads2.1M/mo
TextLikes1K

Speech recognition model from Mistral, 4.4B parameters.

Open weightsApache 2.0758/1040
Mistral

Ministral 3 8B

CTX262K
Vision · Tools
TextImageInput$0.15/M
TextOutput$0.15/M

Compact open vision-language model for edge deployment, instruction following, and tool use

Open weightsApache 2.0715/1040
Mistral

Ministral 3 3B

CTX131K
Vision · Tools
TextImageInput$0.10/M
TextOutput$0.10/M

Compact open vision-language model for edge deployment, instruction following, and tool use

Open weightsApache 2.0714/1040
Mistral

Ministral 3 14B

CTX262K
Vision · Tools
TextImageInput$0.20/M
TextOutput$0.20/M

Open vision-language model for efficient local deployment, instruction following, and tool use

Open weightsApache 2.0713/1040
Mistral

Devstral-Small-2-24B-Instruct-2512

SIZE24B
Text
TextDownloads270K/mo
TextLikes700

Language model from Mistral, 24B parameters.

Open weightsApache 2.0709/1040
Deck0/4
  1. Empty slot
  2. Empty slot
  3. Empty slot
  4. Empty slot