Offload an LLM call from an Inngest function with step.ai.infer or step.ai.wrap

Documented steps

1. Use `step.ai.infer` to have Inngest make the provider request on your behalf: `const response = await step.ai.infer("call-openai", { model: step.ai.models.openai({ model: "gpt-4o" }), body: { messages: [{ role: "assistant", content: "..." }] } });`
2. Supported adapters for `step.ai.infer`: OpenAI (including OpenAI-compatible endpoints such as Perplexity), Anthropic, Gemini, Grok and Azure OpenAI.
3. Configure provider credentials via the adapter or its default env var — `openai()` falls back to `OPENAI_API_KEY`, `anthropic()` to `ANTHROPIC_API_KEY`, `gemini()` to `GOOGLE_API_KEY`. Authentication originates from your own function; Inngest states it never logs or stores your keys.
4. For the Anthropic adapter, `defaultParameters.max_tokens` is required.
5. Use `step.ai.wrap` instead when you want to keep an existing SDK call (e.g. Vercel AI SDK): `const { text } = await step.ai.wrap("using-vercel-ai", generateText, { model: openai("gpt-4-turbo"), prompt: "..." });`
6. Ensure all arguments passed to `step.ai.wrap` are JSON-serializable; bind method-style client calls with `.bind()` before wrapping.
7. Pair with a per-provider `concurrency` constraint (`scope: "account"`, static key) so multiple functions share one upstream budget.