Responses API (Reasoning)

Responses API (Reasoning Models)

Use the responses API to query o-series and similar models that provide reasoning efforts.

1 const response = await client.responses.create({
2   model: "openai/o4-mini",
3   input: "Explain the halting problem in two sentences.",
4   reasoning: { effort: "medium" },
5   max_output_tokens: 512,
6 });
7 
8 console.log(response.output);

Streaming works the same way via client.responses.create({ ...stream: true }).

Responses API (Reasoning Models)

Use the responses API to query o-series and similar models that provide reasoning efforts.

1 const response = await client.responses.create({
2   model: "openai/o4-mini",
3   input: "Explain the halting problem in two sentences.",
4   reasoning: { effort: "medium" },
5   max_output_tokens: 512,
6 });
7 
8 console.log(response.output);

Streaming works the same way via client.responses.create({ ...stream: true }).

1	const response = await client.responses.create({
2	model: "openai/o4-mini",
3	input: "Explain the halting problem in two sentences.",
4	reasoning: { effort: "medium" },
5	max_output_tokens: 512,
6	});
7
8	console.log(response.output);