Intron

African-accent speech recognition, multilingual speech synthesis and voice authentication through the commercial Sahara family.

Partial family, named legacy-model and benchmark-version coverage. Current language routes and proprietary checkpoints are not one-to-one; public research weights are excluded.

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.

11 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
Sync upload: at most 120 seconds of audio. Streaming sessions: at most 300 seconds; idle audio gap at most 60 seconds. Async file-duration ceiling not established.audio limit	File transcript and optional post-processing JSON; streaming partial transcript events followed by a committed transcript.output formats	Usage pricing No reviewed public inference tariff. The account-balance API reports NGN for Nigerian accounts and USD for other countries, but a balance or sample balance is not a per-minute, character, token or question price.Rates & conditions ↗	Different billing unitPrice details ↗
Generate/enqueue prose: 4096 characters. Error examples instead mention 100 and 1200 respectively. Confirm the enforced file limit; streaming accepts 10–100 characters per chunk.text input	WAV, OPUSoutput formats	Usage pricing No reviewed public inference tariff. The account-balance API reports NGN for Nigerian accounts and USD for other countries, but a balance or sample balance is not a per-minute, character, token or question price.Rates & 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 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 pricingNot collected	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricing No reviewed public inference tariff. The account-balance API reports NGN for Nigerian accounts and USD for other countries, but a balance or sample balance is not a per-minute, character, token or question price.Rates & conditions ↗	Different billing unitPrice details ↗
Not collected	Product JSON fields depend on selected processing options; get_answer returns transcript_answer and overrides other post-processing tasks.output formats	Usage pricing No reviewed public inference tariff. The account-balance API reports NGN for Nigerian accounts and USD for other countries, but a balance or sample balance is not a per-minute, character, token or question price.Rates & conditions ↗	Task-based pricingPrice 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