A straightforward translation rarely needs a frontier model. Test right-sized models for each language pair against your evals and your translators' review.
Prefer email? hello@azitalabs.com, subject “Workload evaluation: Translation & localisation”
A straightforward translation that a small model handles cleanly still runs on a frontier model, on every request. Each language pair has its own glossary and its own quality bar, clients expect their turnaround, and rate limits and model changes arrive on someone else's schedule.
An example workflow
Government and corporate documents need Hindi and regional language versions that follow a glossary. An evaluation could take approved translations for one language pair, produce drafts, and let the lead translator compare quality and total cost.
An example workflow
Subtitles must fit timing and reading speed as well as meaning. An evaluation could take one delivered subtitle file, produce drafts in each language, and compare the edits needed and the total cost.
An example workflow
App strings change every release and need consistent terminology. An evaluation could run the team's own eval set through right-sized models and compare terminology accuracy, latency and total cost.
Every step is judged against your evals for each language pair. A step that does not pass stays where it is.
Draft translations are checked against your glossary and your translators' style for each language pair.
Each language pair's total cost compared with what you pay today, before you switch.
Run your workload on capacity from Azita’s installations. Scope the workload and data requirements.
Discuss your workload on the fleetScope the room and workload together. Azita designs, installs and commissions the deployment.
Discuss an installation in your buildingWhere the work runs, which models are used, who has access and how long anything is kept are agreed in your proposal before any work starts. The Trust page sets out custody and residency by side.
Agree a representative job and the acceptance criteria. Compare the output, turnaround, data requirements and total cost before deciding.
Available to evaluate on your own workload.
On the Azita fleet, or on an installation in your building.
We'll review what you need to run and contact you to discuss the right setup.
There is no price list. Your proposal states what is being quoted, the commitment and what is included. Human review, software licences and integration are listed wherever they apply.
Add what you pay for today. It travels with your enquiry as a note, so the comparison starts from the same work.
Prefer to read first? How pricing works
Your eval suite decides. We map each step to the smallest model that meets your pass criteria and run the suite on both stacks side by side. A step that does not pass stays where it is.
Send one translation pipeline with its eval set and last month's usage. We agree the pass criteria, run the suite on both stacks, and set out pass rates, latency and total cost for each step.
Your evals run in CI, and you cut over step by step behind your own flags. Any step that does not pass on the new stack stays with your current provider.
On the Azita fleet, or on an installation in your own building. Where your client documents are processed, who has access and how long anything is kept are agreed in your proposal before any work starts.
Proposal based on your workload and deployment. It states what is being quoted, the commitment and what is included, and lists human review, software licences and integration wherever they apply. There is no price list.
Term, what is included, exit and data handling at the end are set out in your agreement before you sign.
Related
Engineering and product
Agents, support, extraction and product features, tested on your own evals.
The page for every kind of work in this group, and how an evaluation works.
Read
Also for
OTT & production house
Dubbing, subtitling and trailer cutdowns, evaluated on an episode you already delivered. Compare the output and total cost before you switch.
Read
Also for
E-commerce catalogues
Attribute extraction, product descriptions and photo clean-up, tested on listings you already published. Compare quality and total cost first.
Read
A production workflow and its eval set. We agree the pass criteria, then compare output, latency and total cost on the same input.
Arrange a workload evaluation