Voxtral Small 24B 2507

Other33K context

Open weightsTool calling
Lowest · Amazon Bedrock Converse
$0.10 / $0.30
per 1M in / outPricing page

As of Nov 18, 2026, Voxtral Small 24B 2507 costs $0.10 per million input tokens and $0.30 per million output tokens from Amazon Bedrock Converse. The cheapest of 3 providers is Amazon Bedrock Converse at $0.10 / $0.30. No price change since Appndo started tracking it on Oct 14, 2026. Recent price changes

Providers (3)

Sorted by your monthly estimate. Prices per million tokens. Amazon Bedrock Converse also lists batch $0.05 / $0.15 and up to 8K output tokens per request.

  • Input / output
    $0.10 / $0.30
    Context
    33K
    Per month
    $1.60

    mistral.voxtral-small-24b-2507

  • Input / output
    $0.10 / $0.30
    Context
    33K
    Per month
    $1.60

    bedrock_mantle/mistral.voxtral-small-24b-2507

  • Input / output
    $0.10 / $0.30
    Context
    33K
    Per month
    $1.60

    mistralai/voxtral-small-24b-2507

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

Similar models

Common questions

How much does the Voxtral Small 24B 2507 API cost?

As of Nov 18, 2026, Voxtral Small 24B 2507 costs $0.10 per million input tokens and $0.30 per million output tokens from Amazon Bedrock Converse.

Where is Voxtral Small 24B 2507 cheapest?

As of Nov 18, 2026, the cheapest of 3 providers is Amazon Bedrock Converse at $0.10 per million input tokens and $0.30 per million output tokens. Appndo lists no official price from Other.

What is the context length of Voxtral Small 24B 2507?

Voxtral Small 24B 2507 takes up to 33K tokens of context at Amazon Bedrock Converse.

How does Voxtral Small 24B 2507 compare with similar models?

Voxtral Small 24B 2507 has no LMArena score yet. Other Other models and their cheapest price per million input / output tokens: Beam 1.0 501B A23B ($0.30 / $1.00) and Ripple 65B Preview ($0.20 / $0.60).

About this data

Prices come from LiteLLM's model cost map, with more providers from models.dev (both MIT licence), checked Nov 18, 2026; confirm on the provider's pricing page before you rely on a number.