Mixtral-8x22B-Instruct-v0.1 vs Mistral Large

API pricing, benchmark indices and specs — updated 19 October 2026.

mistralai · A · Open weights

Params

140.6 B

Context

65,536

30d

46 K

apache-2.0 · commercial OK

mistralai · B · API-only

Input / 1M

$2.00

Output / 1M

$6.00

AA index

5.8

proprietary · 128K context

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Mixtral-8x22B-Instruct-v0.1	Mistral Large
Deployment	Open weights · also via API	API-only (closed weights)
Parameters	140.6 B	n/a — API-only
Architecture	MixtralForCausalLM	n/a — API-only
Context length	65,536	128,000
Licence	apache-2.0	Proprietary
Commercial use	Allowed	Per API terms
Languages	5	n/a — API-only
Downloads 30d	46,472	n/a — API-only
Downloads all time	6.3 M	n/a — API-only
Quantizations on the Hub	SAFETENSORS	n/a — API-only
Gated	No	n/a — API-only
First seen on the Hub	2024-04-16	n/a — API-only
API input price / 1M tokens	$2.00	$2.00
API output price / 1M tokens	$6.00	$6.00
Est. cost per 1M input + 1M output tokens	$8.00	$8.00
Cached input / 1M tokens	$0.20	$0.20
AA Intelligence Index	5.7	5.8
AA Coding Index	—	—
AA Agentic Index	—	—
Max output tokens	52,428	102,400
API providers	1	1
Tool calling	Yes	Yes
Reasoning mode	No	No

Estimated cost of 1M input + 1M output tokens via OpenRouter

Mixtral-8x22B-Instruct-v0.1 $8.00

Mistral Large $8.00

On RTX 4090 · 24 GB · 8K context unless noted

Mixtral-8x22B-Instruct-v0.1 · fp16 331.0 GB / 24 GB

❌ Won’t fit