Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Smallest AI / Electron

Electron

Text-only conversational LLM for voice-agent pipelines, with tool calls, JSON object output and automatic prefix caching.

Language models (LLMs)
restrictedClosed weightsText generationAgents
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
11 of 18 specification fields collected
Context window32.8K32,768 tokens
Maximum outputNot collectedAwaiting source review
Input billingSee billing notesSmallest AI API
Output billingSee billing notesAccess and billing notes below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
32,768 tokensSource for Context / input limit (opens in a new tab)

Combined input plus output. No independent output maximum has been verified.

Maximum output
Not collected
Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
TextSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
SupportedSource for Tool calling (opens in a new tab)

Includes parallel calls and optional spoken filler content alongside tool calls.

Structured output
SupportedSource for Structured output (opens in a new tab)

JSON object mode; not evidence of strict JSON Schema output.

Streaming
SupportedSource for Streaming (opens in a new tab)
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Causal language modelSource for Architecture (opens in a new tab)
Languages
View all 70 entries
  • English
  • Spanish
  • French
  • German
  • Italian
  • Portuguese
  • Dutch
  • Catalan
  • Hindi
  • Bengali
  • Tamil
  • Telugu
  • Marathi
  • Gujarati
  • Kannada
  • Malayalam
  • Punjabi
  • Odia
  • Urdu
  • Polish
  • Russian
  • Ukrainian
  • Belarusian
  • Czech
  • Slovak
  • Romanian
  • Hungarian
  • Bulgarian
  • Croatian
  • Serbian
  • Slovenian
  • Macedonian
  • Albanian
  • Estonian
  • Latvian
  • Lithuanian
  • Swedish
  • Norwegian
  • Danish
  • Finnish
  • Icelandic
  • Greek
  • Turkish
  • Arabic
  • Hebrew
  • Persian (Farsi)
  • Kurdish
  • Chinese (Simplified)
  • Chinese (Traditional)
  • Japanese
  • Korean
  • Mongolian
  • Vietnamese
  • Thai
  • Indonesian
  • Malay
  • Filipino
  • Burmese
  • Khmer
  • Lao
  • Nepali
  • Sinhala
  • Kazakh
  • Uzbek
  • Swahili
  • Amharic
  • Afrikaans
  • Yoruba
  • Hausa
  • Zulu
Source for Languages (opens in a new tab)
Context caching
SupportedSource for Context caching (opens in a new tab)
latency
Under 300 ms time to first token on a warm connectionSource for latency (opens in a new tab)

Provider-reported typical latency, not an SLA.

Published price
Custom token pricing; contact Smallest AISource for Published price (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Smallest AI API

Provider source (opens in a new tab)
API model ID
electron
Access
POST https://api.smallest.ai/waves/v1/chat/completions. OpenAI-compatible text chat with optional SSE streaming; request enterprise access.
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.
Request quotas
Card lists 10 RPM / 3 in-flight on Standard and 200 RPM / 20 in-flight on Enterprise; actual entitlement requires confirmationSource for Request quotas (opens in a new tab)
Billing basis
Input/output tokens, with a discounted cached-input rate; contact account manager for numbersSource for Billing basis (opens in a new tab)

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Content is retained unless an eligible Enterprise data policy is enabled. Options: no content storage, a 24-hour to 90-day window, or x-expire-content: true for seven-day expiry. On other plans the header is ignored. Billing/usage metadata remains; settings are not retroactive. TTS saved history is excluded from window expiry. Speech-to-speech and cloning are not expressly covered.

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 INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Smallest AI API

electron
Documented
Support evidence (opens in a new tab)
How it works
Automatic identical-prefix reuseSource for How it works (opens in a new tab)
Minimum reusable input
Not collected

No explicit minimum cacheable prefix length verified; example token counts are not thresholds.

Lifetime & refresh
Expires after inactivity; hot entries remain cachedSource for Lifetime & refresh (opens in a new tab)

No numeric TTL or retention guarantee published.

How to enable it
No opt-in flag. Put stable system messages and context before variable input.Source for How to enable it (opens in a new tab)
Usage fields
usage.prompt_tokens_details.cached_tokensSource for Usage fields (opens in a new tab)
Billing rules
Cached input tokens receive a discount; numeric rates by account agreementSource for Billing rules (opens in a new tab)
Limits & data boundaries
Token content and message order must match. Whitespace, punctuation and capitalization changes can invalidate reuse.Source for Limits & data boundaries (opens in a new tab)

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 13 Oct 2026

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)

Sources reviewed