All models

Mixtral 8x22b Instruct

Mistral AIOpen weights66K contextTool calling

As of Oct 14, 2026, Mixtral 8x22b Instruct costs $1.20 per million input tokens and $1.20 per million output tokens from Vercel AI Gateway. The cheapest of 3 sellers is Vercel AI Gateway at $1.20 / $1.20.

Lowest price, from Fireworks AI

Per million tokens

Input
$1.20
Output
$1.20
Cached input
—
Batch input / output
—
  • Up to 66K output tokens per request.

Estimate your monthly cost

Est. per month = input tokens × input price + output tokens × output price. Prices are per million tokens, so 10M input tokens at $3.00 cost $30.

From Fireworks AI: $14.40 a month.

Where to buy it (3)

Sorted by your monthly estimate. Prices per million tokens.

  • Input / output
    $1.20 / $1.20
    Context
    66K
    Per month
    $14.40

    fireworks_ai/accounts/fireworks/models/mixtral-8x22b

  • Input / output
    $1.20 / $1.20
    Context
    66K
    Per month
    $14.40

    fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct

  • Input / output
    $1.20 / $1.20
    Context
    66K
    Per month
    $14.40

    vercel_ai_gateway/mistral/mixtral-8x22b-instruct

  • Input / output
    $2.00 / $6.00
    Context
    66K
    Per month
    $32.00

    mistralai/mixtral-8x22b-instruct

Cloud and hosted sellers may add regional pricing, minimums or platform fees. Supports: Tool calling.

Similar models

About this data

Prices come from LiteLLM's model cost map, with more sellers from models.dev (both MIT licence), checked Oct 14, 2026; confirm on the seller's pricing page before you rely on a number.