[URGENT] GPT-4.1-mini consumes unknown amount of input tokens

API Bugs
,
7

I tested on both chat completions api and responses api. This is related only to gpt-4.1-mini.

There you have a minimal reproduction using sdk

const response = await this.openai.responses.create({
            model: "gpt-4.1-mini",
            input: [
                {
                    type: "message",
                    role: "developer",
                    content: [{ type: "input_text", text: "You are a helpful assistant." }],
                },
                {
                    type: "message",
                    role: "user",
                    content: [{ type: "input_text", text: "What's the status of task #1?" }],
                },
            ],
            store: true,
            tools: [
                {
                    type: "function",
                    name: "get_locations",
                    parameters: zodToJsonSchema(
                        z.object({}),
                    ),
                    strict: true,
                },
                {
                    type: 'function',
                    name: "get_weather",
                    parameters: zodToJsonSchema(
                        z.object({
                            location: z.string(),
                            temperature: z.number(),
                        }),
                    ),
                    strict: true,
                },
            ],
            text: {
                format: {
                    type: "json_schema",
                    name: "weather-report",
                    schema: zodToJsonSchema(
                        z.object({
                            items: z.array(z.object({
                                location: z.string(),
                                temperature: z.number(),
                            })),
                        }),
                    ),
                    strict: true,
                }
            }
        });