/**
 * Model IDs accepted by `POST /v2/responses` (case-sensitive; unknown ids return `404`):
 *
 * - **`sarvam-105b`** — Sarvam flagship model.
 * - **`sarvam-105b-conversations`** — Sarvam 105B tuned for real-time dialogue.
 * - **`glm5.3`** — 1,048,576-token context; reasoning in `output` as a `reasoning` item; flat function tools; max request size 10,485,760 bytes.
 * - **`glm5.3-flash`** — long context, vision (inline base64 images), tools, and reasoning; `reasoning.effort` accepts `low` or `high` only, as on `glm5.3`.
 * - **`gemma4`** — 262,144-token context, vision (inline base64 images), tools, and optional reasoning (`reasoning.effort` `low` or `high`).
 * - **`deepseekv4.1-flash-1017`** — long context, vision (inline base64 images), tools, and reasoning.
 * - **`deepseekv4.1-flash-1017-interactive`** — same capabilities as `deepseekv4.1-flash-1017`, on a high-throughput deployment (more than 200 output tokens per second).
 * - **`deepseekv4-pro`** (Provisioned Throughput) — long context, text input, tools, and reasoning (default `high`).
 * - **`kimi-k3.1-pro`** (Provisioned Throughput) — long context, image input (inline base64; no video on this route), tools, and reasoning (always on).
 * - **`qwen38-27b`** (Provisioned Throughput) — 262,144-token context, image input (inline base64), tools, and reasoning (on by default).
 */
export declare const ResponsesModelIds: {
    readonly Sarvam105B: "sarvam-105b";
    readonly Sarvam105BConversations: "sarvam-105b-conversations";
    readonly Glm53: "glm5.3";
    readonly Glm53Flash: "glm5.3-flash";
    readonly Gemma4: "gemma4";
    readonly Deepseekv41Flash1017: "deepseekv4.1-flash-1017";
    readonly Deepseekv41Flash1017Interactive: "deepseekv4.1-flash-1017-interactive";
    readonly Deepseekv4Pro: "deepseekv4-pro";
    readonly KimiK31Pro: "kimi-k3.1-pro";
    readonly Qwen3827B: "qwen38-27b";
};
export type ResponsesModelIds = (typeof ResponsesModelIds)[keyof typeof ResponsesModelIds];