Providers & pricing
| Provider | Input | Output | Free tier |
|---|---|---|---|
 AWS Default | 30.2 RODI/M~0.0400 USD/M | 30.2 RODI/M | — |
Pricing
| Rate | RODI | USD (ref.) | Unit |
|---|---|---|---|
| In | 30.2 | ~ 0.0400 | USD/M · RODI/M |
| Out | 30.2 | ~ 0.0400 | USD/M · RODI/M |
RODI prices include RodiumAi markup and upstream fees. USD figures are wholesale reference rates.
Capabilities
Streaming
Tool calling
Vision
JSON mode
Reasoning
About this model
Speech-centric Voxtral model on Amazon Bedrock. Compact 3B voice assistant for low-latency ASR, spoken-language understanding, and text responses via Converse (audio + text in, text out).
API usage
Transcribe audio with client.transcribe() — multipart POST /v1/audio/transcriptions.
RodiumAi SDK
transcribe() uploads a local audio file via multipart form.
…Compatible SDKs (OpenAI / Anthropic packages)
…