/ Smallest AI / Hydra v1.1 Smallest AI / Hydra
Hydra v1.1 Full-duplex English audio conversation with interruptions and client-executed tool calls over one WebSocket.
preview Closed weights Speech-to-speech Voice conversation
Output formats PCM16 signed little-endian, mono, base64 JSON frames See specification notes below
Languages 1 listed Full language list in specifications
Input billing See billing notes Smallest AI API
Output billing See billing notes Access and billing notes below
Specifications Access & pricing Caching Voices Evaluation Sources & lifecycle
Specifications Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.
Context / input limit Not collected
Maximum output Not collected
Reasoning Not collected
Structured output Not collected
Batch processing Not collected
Fine-tuning Not collected
Knowledge cutoff Not collected
Parameters Not collected
Architecture Not collected
Context caching Not collected
Access & pricing Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
API model ID hydra-v1.1
Access wss://api.smallest.ai/waves/v1/s2s?model=hydra-v1.1. API key or short-lived token; browser clients should mint tokens server-side.
Regions Automatic routing to Mumbai, India or Oregon, USA; api.india.smallest.ai and api.us.smallest.ai pin a region. Language availability can differ by region. Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms The published zero-retention contract expressly lists TTS, STT and LLM APIs. It does not establish coverage for Hydra speech-to-speech or voice cloning; confirm terms with the account team.
Read the service policy (opens in a new tab)
Caching Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
01 / INITIAL INPUT Process & retain The system processes eligible input and retains reusable state.
02 / LATER REQUEST Check available state Reuse depends on matching input, session state and the cache policy.
03 / CACHE HIT Reuse & generate Reusing state can reduce repeated work. Any charges follow the billing rules below.
Smallest AI API hydra-v1.1Not verified No discounted prompt-cache contract verified for this model/access route. Audio continuity and model-weight storage are separate features.
How it works Not collected No discounted prompt-cache contract verified for this model/access route. Audio continuity and model-weight storage are separate features.
Minimum reusable input Not collected No discounted prompt-cache contract verified for this model/access route. Audio continuity and model-weight storage are separate features.
Lifetime & refresh Not collected No discounted prompt-cache contract verified for this model/access route. Audio continuity and model-weight storage are separate features.
How to enable it Not collected No discounted prompt-cache contract verified for this model/access route. Audio continuity and model-weight storage are separate features.
Usage fields Not collected No discounted prompt-cache contract verified for this model/access route. Audio continuity and model-weight storage are separate features.
Billing rules Not collected No discounted prompt-cache contract verified for this model/access route. Audio continuity and model-weight storage are separate features.
Limits & data boundaries Not collected No discounted prompt-cache contract verified for this model/access route. Audio continuity and model-weight storage are separate features.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
What the measurements say No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.
Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.
The record behind the model Why it is included Smallest retains rights in its AI models and prohibits model extraction. Its model cards name Smallest as developer; Electron, Hydra and Lightning v3.1 explicitly use proprietary licenses. Commercial self-hosting requires licensed artifacts and a license proxy, not an open-weight grant.
Classification evidence (opens in a new tab) Lifecycle dates Sources reviewed Model notes Seven TTS registry identities, three Pulse models, Electron and both documented Hydra versions reviewed. Private variants, conflicting tariffs, legacy endpoint availability and v4 beta API contracts remain under review.
Pricing page labels Hydra beta. The card documents served versions; access remains subject to the account plan.
The unversioned hydra alias maps to v1.0 and is deprecated. Its voice roster differs from v1.1, so switching only the model tag is insufficient.
No transcript is returned on the native session wire. Use a separate STT service if a transcript is required. JSON-schema tool definitions do not prove strict structured answer output.
Provider benchmark numbers on the family card are not pinned to a version and are not assigned as per-version quality ratings.
Check against your workload Try representative inputs, measure task success and total cost, then check the exact endpoint’s data policy.
Read our methodology
Also from Smallest AI Lightning V4 Lightning V3.2 Lightning V3.1 Pro Lightning V3.1 Lightning V2 Lightning Large Lightning Pulse Pulse Pro Pulse 2.0 Electron Hydra v1.0 