Fireworks

FireworksModel reads FIREWORKS_API_KEY and targets https://api.fireworks.ai/inference/v1.

let model = FireworksModel("accounts/fireworks/models/glm-5p2")
let result = streamText(model: model, prompt: "Say hello.")

for try await text in result.textStream {
  print(text, terminator: "")
}

Fireworks accepts low, medium, and high reasoning effort, so .minimal becomes low and .xhigh becomes high. Other capabilities depend on the selected model.

Models

Current serverless examples include:

The catalog rotates, and custom deployments use account-qualified IDs. Browse the live Fireworks model library and serverless serving-path documentation before pinning a model in production.