import type * as SarvamAI from "../../../../index.js";
/**
 * @example
 *     {
 *         model: "sarvam-105b",
 *         input: "input"
 *     }
 */
export interface ResponsesCreateRequest {
    model: SarvamAI.ResponsesModelIds;
    input: SarvamAI.ResponseInput;
    /** Maximum output tokens to generate, including reasoning tokens on reasoning models. If omitted, there is no default cap — generation is unbounded and continues until the model stops on its own or the context window fills. Always set this explicitly in production. Values above the model context window return `400`. */
    max_output_tokens?: number;
    /** Sampling temperature between 0 and 2. Default **`1`** on `glm5.3` when omitted. Output is not bit-reproducible, even at `0`. */
    temperature?: number;
    /** Must be `false` or omitted (omitting is `200` and echoed as `false`). `true` is `400 invalid_request_error` — nothing created here is retrievable. OpenAI SDKs default this to `true`, so a default `client.responses.create(...)` fails. */
    store?: boolean;
    /** Function tools use the **flat** Responses shape (`type`, `name`, `parameters`, `strict`) — the nested chat-completions tool shape is **`400`**. `tool_choice: required` with no tools returns **`400`**. Function `arguments` in output are a JSON **string** (parse before use). Multiple tool calls per turn are supported; use **`parallel_tool_calls: true`** or omit (see that field). */
    tools?: SarvamAI.ResponseFunctionTool[];
    /** Forwarded exactly as written: `none`, `auto`, `required`, `{ "type": "function", "name": "..." }`, or another object. */
    tool_choice?: ResponsesCreateRequest.ToolChoice;
    /** Optional reasoning config for `glm5.3`, `glm5.3-flash`, `gemma4`, the DeepSeek models, `kimi-k3.1-pro`, and `qwen38-27b`. **`effort`:** on `glm5.3` and `glm5.3-flash`, `low` or `high` only (the literal string `max` returns `400`; omitting it gives `max` on `glm5.3` and `high` on `glm5.3-flash`); on `deepseekv4.1-flash-1017`, `deepseekv4.1-flash-1017-interactive`, and `deepseekv4-pro`, `low`, `high`, `max`, or `none` (thinking off); on `kimi-k3.1-pro`, `low`, `medium`, `high`, or `max` (thinking is always on); on `qwen38-27b`, `none` turns thinking off. The trace is in the reasoning item's `content[0].text`; `summary` is filled only when `summary` is set. Optional **`summary`:** `auto` or `detailed`. */
    reasoning?: SarvamAI.ResponseReasoning;
    /** Merged into the outbound body. Must not overwrite any modelled field (`400`). `max_tool_calls` and `prompt` are `400` here and in `extra_body` — not supported by any serving deployment. */
    extra_body?: Record<string, unknown>;
    /** System-style instructions. Echoed back on the response object when set. */
    instructions?: string;
    /** Nucleus sampling. Default **`0.95`** on `glm5.3` when omitted. Must be greater than **`0`** and at most **`1`** (`0` is rejected on `glm5.3`). */
    top_p?: number;
    /** Not supported on the Responses route for `glm5.3`; any value returns **`400`**. */
    top_k?: number;
    /** Optional. Range `-2` to `2`. May be accepted and echoed on Responses without changing model output. */
    frequency_penalty?: number;
    /** Optional. Range `-2` to `2`. May be accepted and echoed on Responses without changing model output. */
    presence_penalty?: number;
    /** Output format, set in `format` (`text`, `json_object`, or `json_schema`). */
    text?: SarvamAI.ResponseTextConfig;
    /** **`false`** limits a turn to a single tool call on every open-weight model. `sarvam-105b` ignores it on this route. */
    parallel_tool_calls?: boolean;
    /** **Ignored** on this route — Responses always returns one output. Accepted for OpenAI SDK compatibility only; omit or leave at `1`. */
    n?: number;
    /** **Ignored** on Responses. Accepted for SDK compatibility only. */
    seed?: number;
    /** `400 invalid_request_error`. This endpoint holds no state — replay the conversation in `input`. OpenAI and Fireworks use this to continue a chat; we do not. */
    previous_response_id?: string;
    conversation?: SarvamAI.ResponseConversation;
    /** `true` is `400 invalid_request_error`. This endpoint is synchronous only. */
    background?: boolean;
    /** `400 invalid_request_error` — not supported by any serving deployment, top-level or via `extra_body`. */
    max_tool_calls?: number;
    /** How many of the most likely tokens to return at each output position, with their log probabilities. Send it with `include: ["message.output_text.logprobs"]`; without `include`, `output[].content[].logprobs` comes back empty. `0` returns no logprobs. Supported on `sarvam-105b`, `glm5.3-flash`, `deepseekv4.1-flash-1017`, `deepseekv4.1-flash-1017-interactive`, `deepseekv4-pro`, and `qwen38-27b`; `glm5.3`, `gemma4`, and `kimi-k3.1-pro` return `400`. */
    top_logprobs?: number;
    /** Extra data to add to the response. `message.output_text.logprobs` returns token log probabilities (use with `top_logprobs`); `reasoning.encrypted_content` is accepted. An unknown value returns `400`. */
    include?: string[];
    /** Accepts any additional properties */
    [key: string]: any;
}
export declare namespace ResponsesCreateRequest {
    /**
     * Forwarded exactly as written: `none`, `auto`, `required`, `{ "type": "function", "name": "..." }`, or another object.
     */
    type ToolChoice = SarvamAI.ToolChoiceOption | Record<string, unknown>;
}