Smallest AI

Proprietary Lightning speech synthesis, Pulse transcription, Electron language and Hydra full-duplex speech models, with commercial self-host options.

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.

Closed-weight models

Browse by model typeCapabilities can overlap

Start with the job your model needs to do. Then narrow by capabilities, provider and price.

Select up to 3 models to compare

What does one question cost?

Compare every model with the same request.

Input tokensOutput tokens

Estimate = (input tokens × input price + output tokens × output price) / 1,000,000. Include conversation history in input and billed reasoning in output. Input-only decision models ignore the output setting; enter all billed input for one decision, including its question and criteria. Media, tools and discounts are separate.

13 models

Sort by

Model input and output limits, prices and estimated cost per question at the selected token counts.
Input tokensPublished limit*	Output tokensMaximum per response*	Input pricePer 1M tokens	Cost per question1,000 input + 500 outputEstimated · uncached
Not collected	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗
Not collected	PCM16 monooutput formats	Usage pricingNot collected	Different billing unitPrice details ↗
Not collected	PCM, MP3, WAV, ulaw, alawoutput formats	Usage pricing $0.195 / 10,000 characterspayg character rate · Smallest AI APIRates & conditions ↗	Different billing unitPrice details ↗
Not collected	PCM, MP3, WAV, ulaw, alawoutput formats	Usage pricing $0.175 / 10,000 characterspayg character rate · Smallest AI APIRates & conditions ↗	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricing $0.003 / audio minutepublished payg · Smallest AI API$0.005 / audio minutecompare page rate · Smallest AI APIPublished rates conflict. Compare the source and transport before estimating spend.Rates & conditions ↗	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricing $0.004 / audio minutestandard model card · Smallest AI API$0.0035 / audio minutemarketing table rate · Smallest AI APIPublished rates conflict. Compare the source and transport before estimating spend.Rates & conditions ↗	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricing $0.005 / audio minutestandard model card · Smallest AI APIRates & conditions ↗	Different billing unitPrice details ↗
32,768context tokens	Not collected	Usage pricing Custom token pricing; contact Smallest AIRates & conditions ↗	Needs rate detailsPrice details ↗
Not collected	PCM16 signed little-endian, mono, base64 JSON framesoutput formats	Usage pricing Custom pricing per session minuteRates & conditions ↗	Different billing unitPrice details ↗
Not collected	PCM16 signed little-endian, mono, base64 JSON framesoutput formats	Usage pricing Custom pricing per session minuteRates & conditions ↗	Different billing unitPrice details ↗

* Media models show their native limits. A shared context window includes both input and output tokens.

Original currency and billing unit, without currency conversion. Rates are dated snapshots; open the conditions for tiers, promotions and endpoint restrictions.How to read the data

Catalog coverage

Closed-weight model variants and explicitly identified closed-source managed model components across language, code, image, video, audio and other documented modalities. Global provider and historical-release coverage is being expanded; this is not yet exhaustive. 172 company reviews are still open.

See what is being reviewed