LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Voxtral Small 24B 2507

mistral·mistral/voxtral-small-24b-2507·GA·Open weights·voxtral series·Speech / Audio
Open audio-language model for speech transcription, audio understanding, and voice-driven tool use

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·Amazon BedrockCloud
$0.10 / $0.30
Blended $0.15 · 2.3× spread
Context
32,768
Output limit
16,384
Knowledge cutoff
2025-07
Released / updated
2025-07-15 / 2025-07-15
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextAudioPDF
License
Apache-2.0
Weights
Hugging Face

Voxtral Small 24B 2507 by mistral is offered by 9 providers on this page. Public prices are shown for 8 of them. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is Amazon Bedrock at $0.10 / $0.30 per 1M. Prices vary about 2.3× across the providers that host it.

The context window is 32,768 tokens at the reference host, but hosts report different limits, from 32,000 to 32,768, so the usable window depends on the provider you pick. It supports tool use and structured output. Accepted input modalities are Text, Audio, and PDF. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-07.

Available at 9 providers8 with public prices

  • ProviderInput / Output
  • Amazon BedrockCloud
    mistral.voxtral-small-24b-2507
    $0.10 / $0.30
    Context 32,768Output limit 8,192deprecated
  • OpenRouterGateway
    $0.10 / $0.30
    Cache read $0.01Context 32,768Output limit 26,214
  • Eden AIGateway
    amazon/mistral.voxtral-small-24b-2507
    $0.10 / $0.30
    Context 32,768Output limit 32,768
  • Eden AIGateway
    amazon/mistral.voxtral-small-24b-2507@us
    $0.10 / $0.30
    Context 32,768Output limit 32,768
  • Kilo GatewayGateway
    $0.10 / $0.30
    Cache read $0.01Context 32,768Output limit 26,214
  • AI/ML APIGateway
    $0.11 / $0.32
    Cache read $0.011Context 32,000 ⚠Output limit 32,000
  • CortecsGateway
    voxtral-small-2507
    $0.12 / $0.37
    Cache read $0.012Context 32,000 ⚠Output limit 32,000
  • GreenPTGateway
    $0.23 / $0.51
    Context 32,768Output limit 16,384deprecated
  • evrocCloud
    mistralai/Voxtral-Small-24B-2507
    — / —
    Context 32,000 ⚠Output limit 32,000hostTable.undisclosed
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Amazon Bedrock
mistral.voxtral-small-24b-2507
Cloud$0.10$0.30——32,7688,192deprecated
OpenRouterGateway$0.10$0.30$0.01—32,76826,214
Eden AI
amazon/mistral.voxtral-small-24b-2507
Gateway$0.10$0.30——32,76832,768
Eden AI
amazon/mistral.voxtral-small-24b-2507@us
Gateway$0.10$0.30——32,76832,768
Kilo GatewayGateway$0.10$0.30$0.01—32,76826,214
AI/ML APIGateway$0.11$0.32$0.011—32,000 ⚠32,000
Cortecs
voxtral-small-2507
Gateway$0.12$0.37$0.012—32,000 ⚠32,000
GreenPTGateway$0.23$0.51——32,76816,384deprecated
evroc
mistralai/Voxtral-Small-24B-2507
Cloud————32,000 ⚠32,000hostTable.undisclosed

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

Common scenarios
1OpenRouter$24.20
2Kilo Gateway$24.20
3AI/ML API$25.60
4Cortecs$29.68
5Amazon Bedrock$35.00
6Eden AI$35.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.15$02026-08-052026-09-29
2026-09-29Input list —Output list —Min blended $0.15

Related models

Voxtral Mini TTS (latest)same series—Voxtral Mini (latest)same series—Voxtral Mini 3B 2507same series—Voxtral Small (latest)same lab$0.10 / $0.40
Data partly from models.dev (MIT)