Gradium

Developer of streaming speech synthesis, recognition and translation, plus Phonon for licensed offline speech generation.

Dated cloud TTS/STT releases, translation and Phonon reviewed. Speech-to-speech is explicitly a managed pipeline. Alias changes, historical availability and unpinned private deployments prevent a complete checkpoint inventory claim.

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.

10 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	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗
Free tier: 1,500 characters per session. A paid-tier character cap is not established.text input	WAV, PCM, Ogg Opus, PCM 8/16/22.05/24/44.1/48 kHz, 8 kHz mu-law / A-lawoutput formats	Usage pricing $69.00 / 1M charactersSpeech synthesis · XS overage · Gradium API$13.00 / monthPlan fee · XS · Gradium APIRates & conditions ↗	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗
Not collected	Transcript text with timing events; REST returns newline-delimited JSON after reading the full audio bodyoutput formats	Usage pricing $0.7452 / audio hourTranscription · XS overage · Gradium API$13.00 / monthPlan fee · XS · Gradium APIRates & conditions ↗	Different billing unitPrice details ↗
Not collected	Transcript text with timing events; REST returns newline-delimited JSON after reading the full audio bodyoutput formats	Usage pricing $0.9936 / audio hourSpeech translation · XS overage · Gradium API$13.00 / monthPlan fee · XS · Gradium APIRates & conditions ↗	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricing $3.726 / audio hourSpeech translation · XS overage · Gradium API$13.00 / monthPlan fee · XS · Gradium APIRates & conditions ↗	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricing Negotiated fixed license per device and model type, with unlimited generations under that deployment scope; numeric rates not published.Rates & conditions ↗	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricing Negotiated fixed license per device and model type, with unlimited generations under that deployment scope; numeric rates not published.Rates & 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