Deepgram API offers 4 tracked models (0 with output token pricing). This catalog covers vision; open any model detail page for benchmarks, batch tiers, and migration prompts.
Covers 1 workload area across 4 tracked models; last verified 2026-10-17.
Use it for
- Operators routing vision workloads through this API
Do not use it for
- Final benchmark picks without opening the relevant model detail page
- Strict price-per-token comparisons until output pricing is sourced
Tracked models
4
Models available through this provider
Priced output routes
0
Output pricing not yet tracked
Cheapest output
Unknown
Output pricing not yet tracked
Batch-ready models
0
No batch pricing tracked
Latest model release
2025-10-15
370d since newest release
Freshness
2026-10-17
Researched 3d ago
Information
Deepgram's API provides hosted speech-to-text, text-to-speech, and voice-agent audio models, including Nova, Flux, and Aura model families.
Read more ->Where this host wins
- Vision: 3 tracked models with multimodal benchmark coverage.
Getting started
Platform Overview
Deepgram's API provides hosted speech-to-text, text-to-speech, and voice-agent audio models, including Nova, Flux, and Aura model families.
Available Models(4)
View all →All models available as Serverless
| Model | Image (medium) |
|---|---|
| Deepgram Flux | $0.0065/min |
| Deepgram Aura-2 | — |
| Deepgram Nova-3 | $0.0048/min |
| Deepgram Nova-2 | $0.0043/min |