Nemotron 3.5 Transcribe 30B A4B
Nemotron 3.5 Transcribe is an open-weight 30B-A4B speech-augmented language model from NVIDIA for offline transcription in 40 languages. It handles recordings up to one hour and adds speech translation, contextual and speaker-attributed transcription, word timestamps and audio question answering, leading open-weight models on English, long-form and multilingual ASR.
Model card on Hugging Face- Input price
- $0.000033 per second
- Context
- 4K tokens
- Released
- Oct 28, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
3 providers, cheapest first, OpenRouter last, priced after gateway discounts.
| Provider | Input | Output |
|---|---|---|
DeepInfra deepinfra/nemotron-3.5-transcribe | $0.000033/second | — |
Prime Intellect prime_intellect/nvidia/nemotron-3.5-transcribe-30b-a4b | $0.001/minute | — |
OpenRouter openrouter/nvidia/nemotron-3.5-transcribe | $0.001/minute | — |
Is a provider down? OpenRouter status
Pricing
Averaged across 3 providers, in USD after gateway discounts.
- Average input
- $0.0007 per second
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Response latency
Lower is better0.6sacross providers
Apps
Use Nemotron 3.5 Transcribe 30B A4B in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Nemotron 3.5 Transcribe 30B A4B FAQ
Short answers, built from the data on this page.
Nemotron 3.5 Transcribe 30B A4B is a model from NVIDIA, released on Oct 28, 2026. Nemotron 3.5 Transcribe is an open-weight 30B-A4B speech-augmented language model from NVIDIA for offline transcription in 40 languages. It handles recordings up to one hour and adds speech translation, contextual and speaker-attributed transcription, word timestamps and audio question answering, leading open-weight models on English, long-form and multilingual ASR.
On the Respan gateway, input starts at $0.000033 per second on DeepInfra, after gateway discounts.
Nemotron 3.5 Transcribe 30B A4B is available through 3 providers: DeepInfra, Prime Intellect, and OpenRouter.
Nemotron 3.5 Transcribe 30B A4B accepts up to 4K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "nemotron-3.5-transcribe-30b-a4b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.