Nova-3 model profile
Evidence snapshot:
Nova-3 is a Deepgram model profile with a no verified token context limit in this snapshot. The dated catalog snapshot records audio, transcription modalities and interfaces for audio input, speech transcription.
Deepgram Nova-3 general-purpose speech-to-text model with monolingual and multilingual transcription support.
Nova-3 is a reference profile: Deepgram publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.
Nova-3 is an independent knowledge profile. It does not claim that Kendr hosts the model, quote a Kendr customer price, promise API availability, or advertise a Kendr routing receipt.
Nova-3 accepts audio and returns transcription. The snapshot records audio input and speech transcription as capabilities or interfaces.
The dated unit-price records list $0.0043 per minute for audio_input. Each figure retains its billable dimension, variant, provider, source, and evidence date.
No comparable third-party benchmark value is present in the 2026-09-06 snapshot. Missing values are not estimated.
No comparable popularity rank or traffic share is present in the 2026-09-06 snapshot. No comparable routing rank or traffic-share observation is attached to this dated profile; missing adoption evidence is not estimated.
Profile data was reviewed for the 2026-09-06 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated.
Profile facts
- Profile type
- Model research profile
- Provider or publisher
- Deepgram
- Context window
- No verified limit
- Snapshot date
- 2026-09-06
- Knowledge cutoff
- Not disclosed
- Reference catalog ID
- deepgram/nova-3
When to pick Nova-3
Nova-3 is a reference profile: Deepgram publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.
Each condition below is derived from this model's own values in the 2026-09-06 snapshot, compared only against models publishing the same field.
- Reach for it when the input is speech. The snapshot records audio input, so recordings can go to this route rather than being transcribed first.
- Look elsewhere when you need to call it through Kendr today. This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr.
- Look elsewhere when you are building an agent. No tool-calling capability is recorded for this model in the snapshot. Agent loops need a route that can call functions.
Context, modalities, and identity
Nova-3 accepts audio and returns transcription. The snapshot records audio input and speech transcription as capabilities or interfaces.
- Provider or publisher
- Deepgram
- Context window
- No verified limit
- Maximum output
- No verified numeric limit
- Input modalities
- audio
- Output modalities
- transcription
- Knowledge cutoff
- Not disclosed
Model overview
Deepgram Nova-3 general-purpose speech-to-text model with monolingual and multilingual transcription support.
- Reference model ID
- deepgram/nova-3
- Canonical version
- deepgram/nova-3-20260714
- Hugging Face ID
- Not separately documented
Capabilities and supported controls
Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route.
- Supported parameters
- No verified parameter list
- audio input
- speech transcription
Dated pricing snapshot
The dated unit-price records list $0.0043 per minute for audio_input. Each figure retains its billable dimension, variant, provider, source, and evidence date.
These are dated third-party reference prices, not Kendr prices or an availability offer. Routes, tiers, caching, region, and provider policy can change the landed price.
- Price date
- 2026-09-06
- Input
- No verified rate
- Cached input
- No verified rate
- Output
- No verified rate
| Billable | Variant | Cost | Unit | Provider | As of |
|---|---|---|---|---|---|
| audio_input | Default | $0.0043 | per minute | Not specified | 2026-09-06 |
Provider routes, performance, and uptime
The snapshot retains 1 provider endpoint. Provider prices, context limits, p50 performance, and uptime can differ by route and are not Kendr guarantees.
- Active provider endpoints
- 1
- Best p50 latency
- No recent metric
- Best p50 throughput
- No recent metric
- Availability with routing
- No recent metric
- Availability without routing
- No recent metric
- Performance date
- 2026-09-06
| Provider | Quantization | Input / 1M | Output / 1M | Cache read / 1M | Context | p50 latency | p50 throughput | Uptime (1d) |
|---|---|---|---|---|---|---|---|---|
| Deepgram | unknown | $4,300 / 1M | $0 / 1M | No verified rate | 0 tokens | No recent p50 | No recent p50 | 100.00% |
Benchmark evidence and limitations
No comparable third-party benchmark value is present in the 2026-09-06 snapshot. Missing values are not estimated.
Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.
Popularity and market context
No comparable popularity rank or traffic share is present in the 2026-09-06 snapshot. No comparable routing rank or traffic-share observation is attached to this dated profile; missing adoption evidence is not estimated.
- Third-party catalog rank
- No verified rank
- Global market share
- Not inferred
- Observation date
- 2026-09-06
Frequently asked questions
When should I use Nova-3?
Nova-3 is a reference profile: Deepgram publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call. Reach for it when the input is speech: The snapshot records audio input, so recordings can go to this route rather than being transcribed first. Look elsewhere when you need to call it through Kendr today: This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr. Look elsewhere when you are building an agent: No tool-calling capability is recorded for this model in the snapshot. Agent loops need a route that can call functions.
What is Nova-3?
Nova-3 is a Deepgram model profile with a no verified token context limit in this snapshot. The dated catalog snapshot records audio, transcription modalities and interfaces for audio input, speech transcription.
Does Nova-3 have a verified token context window?
No comparable token context window is present in this dated profile. The page reports audio inputs, transcription outputs, and source-backed modality limits instead of inventing a token limit.
What benchmark evidence is available for Nova-3?
No comparable third-party benchmark value is present in the 2026-09-06 snapshot. Missing values are not estimated. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.
Is Nova-3 available through Kendr?
This is an independent knowledge profile, not a Kendr-hosted availability claim. Check Kendr's live public model API for currently enabled Kendr aliases.
Does the popularity rank represent Nova-3's global market share?
No comparable popularity rank or traffic share is present in the 2026-09-06 snapshot. No comparable routing rank or traffic-share observation is attached to this dated profile; missing adoption evidence is not estimated. No global market-share percentage is inferred when the source does not publish one.
Sources and evidence dates
- Nova-3 third-party catalog record (catalog, checked 2026-09-06)
- Third-party model catalog methodology (methodology, checked 2026-09-06)
- Deepgram official model documentation (primary, checked 2026-09-06)
- Nova-3 third-party catalog record (catalog, checked 2026-09-06)