Use cases

Production AI, one workload at a time.

For each workload: what drives the cost, which model to use, what the API needs to support and how to switch from Anthropic or OpenAI.

Workload
AllCustomer-facingInternal teamsEngineeringData pipelines
Model
AllHalClarkeTycho
Use cases
Internal teams

Internal Copilots

Run internal copilots on Clarke at $1.50 / $7.00 per 1M tokens, with streaming and tool calling. Change the base URL, key and model.

Clarke
$1.50 input / $7.00 output
→
Data pipelines

Document Extraction and Classification

Run document extraction and classification on Tycho at $0.50 / $2.25 per 1M tokens, with JSON schema output. Change the base URL, key and model.

Tycho
$0.50 input / $2.25 output
→
Engineering

Code Review and Code Generation

Run code review and code generation on Clarke at $1.50 / $7.00 per 1M tokens. OpenAI and Anthropic compatible, so you change the base URL, key and model.

Clarke
$1.50 input / $7.00 output
→
Customer-facing

Customer Support Chat

Run customer support chat on Clarke at $1.50 / $7.00 per 1M tokens. OpenAI and Anthropic compatible, so you change the base URL, key and model.

Clarke
$1.50 input / $7.00 output
→
No use cases match these filters yet.