Start typing to search.
nvidia/parakeet-tdt-0.6b-v3
Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture. Trained on the Granary dataset (670,000+ hours of audio), it supports automatic language detection across...
Visual comparison
Compare published endpoint pricing visually.
USD per unit for prompt. Lower is better.
Only directly comparable published units are charted.
Server-rendered comparison
Prices are shown only in the units published by OpenRouter; cross-unit rankings are intentionally omitted. Missing speed data never removes an endpoint.
| Provider / route | Current pricing | Speed measurements | Endpoint details |
|---|---|---|---|
| Provider / route Together together | Current pricing
| Speed measurements
| Endpoint details
10 parametersfrequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, stop, temperature, top_k, top_p |
Endpoint data fetched .
Parakeet TDT 0.6B v3 deployment guide
Parakeet TDT 0.6B v3 is indexed here as a transcription model by NVIDIA, with 1 provider endpoint from Together. The comparison preserves each exact OpenRouter routing tag so pricing and performance observations can be connected to the route an application would actually request.
The model publishes a 0-token context window. It accepts audio input and returns transcription output. 10 distinct supported parameters appear across the listed routes. Confirm limits on the specific endpoint rather than assuming every host exposes the same configuration.
At least one unit is published consistently across the listed endpoints, allowing a direct price chart for prompt. Other charges remain in the table using OpenRouter’s exact billing labels.
Published endpoint formats include unknown. Availability, rate limits, and regional support can change independently of catalog pricing, so confirm the selected routing tag before production deployment.
