← All models
Balanced — strong quality at a mid priceOpen Weights
Voxtral Small 24B 2507 Pricing
Mistral AI · mistralai-voxtral-small-24b-2507
Input / 1M tokens
$0.100
Output / 1M tokens
$0.300
Context window
32k tokens
≈ 43 pages of text
Max output
—
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0002
1,000 requests / month$0.24/mo10,000 requests / month$2.40/mo100,000 requests / month$24.00/moEstimate your own workloadOpens the calculator with Voxtral Small 24B 2507 preloaded — adjust volume and token counts there.
Price history
Only one price point recorded so far.
The staircase chart appears once a price change is detected.
What it excels at
Handles combined text and audio inputs for tasks such as transcription and basic multimodal analysis. Low per-token pricing and open weights support cost-efficient local or private deployment.
The business tradeoff
24B scale and open-weights hosting create variable inference latency and hardware demands. 32k context window restricts use on long audio or document sequences.
Cheaper from Mistral AI
Head-to-head
Vendor list rates, as of Jun 15, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.