> ## Documentation Index > Fetch the complete documentation index at: https://docs.moxus.cloud/llms.txt > Use this file to discover all available pages before exploring further. # Request parameters > Reference common model request parameters, types, ranges, defaults, and meanings. This page summarizes common request parameters for Moxus AI. Whether a parameter takes effect depends on the protocol, selected model, and upstream provider. Unknown or unsupported fields may be ignored by the provider or rejected with a parameter error. Do not mix request bodies across protocols. OpenAI-compatible APIs use `https://moxus.cloud/v1`, Anthropic-compatible APIs use `https://moxus.cloud`, and Google-compatible APIs use `https://moxus.cloud/v1beta`. ## Common fields | Parameter | Type | Required | Default | Range | Meaning | | ---------- | ----------------------- | ----------------------------- | ------- | ---------------- | ------------------------------------------------------------------------- | | `model` | string | Yes | None | - | Model name. Copy the exact name from Model Square. | | `messages` | array | Required for chat / Claude | None | - | Conversation messages. OpenAI and Anthropic message shapes differ. | | `input` | string / array / object | Common for Responses | None | - | Main input field for Responses and some models. | | `prompt` | string / array | Some completion or image APIs | None | - | Single prompt or image generation prompt. | | `stream` | boolean | No | `false` | `true` / `false` | Return streaming responses. | | `metadata` | object | No | None | - | Custom metadata for business tracing. Do not put secrets here. | | `user` | string / object | No | None | - | Client-side user identifier. Some providers support it; others ignore it. | ## Sampling and length | Parameter | Type | Default | Range | Meaning | | ----------------------- | ---------------- | ------------- | ----------- | ----------------------------------------------------------------------------------------------- | | `temperature` | number | Model default | \[0, 2] | Controls randomness. Lower is more stable; higher is more diverse. | | `top_p` | number | Model default | \[0, 1] | Nucleus sampling threshold. Avoid changing both `temperature` and `top_p` aggressively. | | `top_k` | integer / number | Model default | \[1, +∞) | Limits candidate tokens. Common in Anthropic and Google; not always supported by OpenAI models. | | `max_tokens` | integer | Model default | \[0, limit] | Maximum output tokens for Chat Completions and Anthropic-style calls. | | `max_completion_tokens` | integer | Model default | \[0, limit] | Output cap for some newer OpenAI models. | | `max_output_tokens` | integer | Model default | \[0, limit] | Output cap for Responses API and Google-native calls. | | `stop` | string / array | None | - | OpenAI-compatible stop sequence. | | `stop_sequences` | array | None | - | Anthropic / Google native stop sequences. | | `n` | integer | `1` | \[1, +∞) | Number of candidates. More candidates usually cost more. | | `seed` | number / integer | None | - | Attempts deterministic output. Reproducibility depends on model and provider. | ## OpenAI Chat Completions parameters | Parameter | Type | Default | Range | Meaning | | --------------------- | --------------- | ------------- | ---------------------------------------- | ---------------------------------------------------------- | | `messages` | array | None | `system` / `user` / `assistant` / `tool` | Conversation messages. | | `response_format` | object | None | `json_object` / `json_schema` | Ask the model to return JSON or schema-constrained output. | | `tools` | array | None | - | Declares tools the model may call. | | `tool_choice` | string / object | `auto` | `auto` / `none` / `{...}` | Controls whether or which tool is called. | | `parallel_tool_calls` | boolean | Model default | `true` / `false` | Allows multiple tool calls in one response. | | `logprobs` | boolean | `false` | `true` / `false` | Returns token log probabilities if supported. | | `top_logprobs` | integer | None | \[0, 20] | Number of candidate token logprobs per position. | | `frequency_penalty` | number | `0` | \[-2, 2] | Penalizes repeated token frequency. | | `presence_penalty` | number | `0` | \[-2, 2] | Encourages new topics when positive. | | `logit_bias` | object | None | \[-100, 100] | Adjusts likelihood for token IDs. | | `modalities` | array | Model default | `text` / `audio` | Output modalities, depending on model support. | | `audio` | object | None | - | Audio output configuration. | ## OpenAI Responses parameters | Parameter | Type | Default | Range | Meaning | | ---------------------- | --------------- | ---------------- | ------------------------- | ---------------------------------------------------------------------------- | | `input` | string / array | None | - | Main Responses API input. | | `instructions` | string | None | - | Global instructions, similar to a system prompt. | | `previous_response_id` | string | None | - | Continue from a previous Responses call. | | `max_output_tokens` | integer | Model default | \[0, limit] | Maximum output tokens. | | `reasoning` | object | Model default | - | Reasoning configuration for reasoning models. | | `text` | object | Model default | - | Text output format configuration. | | `tools` | array / object | None | - | Responses tool configuration. | | `tool_choice` | string / object | `auto` | `auto` / `none` / `{...}` | Controls tool use. | | `truncation` | string | Model default | `auto` / `disabled` | Behavior when input is too long. | | `include` | array | None | - | Requests additional response fields. | | `store` | boolean | Upstream default | `true` / `false` | Whether upstream may store output. Channel settings may control passthrough. | ## Anthropic-compatible parameters | Parameter | Type | Required | Default | Range | Meaning | | ---------------- | -------------- | ----------------- | ----------------------- | ----------------------------------------------------------------------------------- | ------------------------------------------ | | `model` | string | Yes | None | - | Claude or Anthropic-compatible model name. | | `messages` | array | Yes | None | `user` / `assistant` | Claude Messages content. | | `system` | string / array | No | None | - | System instruction. | | `max_tokens` | integer | Commonly required | None | \[0, limit] | Maximum output tokens. | | `temperature` | number | Model default | \[0, 1] | Controls randomness. Some Claude models may reject non-default sampling parameters. | | | `top_p` | number | Model default | \[0, 1] | Nucleus sampling. | | | `top_k` | integer | Model default | \[1, +∞) | Candidate token limit. | | | `stop_sequences` | array | None | - | Stop sequences. | | | `stream` | boolean | `false` | `true` / `false` | Return streaming response. | | | `tools` | array | None | - | Declares Claude tools. | | | `tool_choice` | object | `auto` | `auto` / `any` / `tool` | Controls tool selection. | | | `thinking` | object | Model default | `enabled` / `disabled` | Claude thinking configuration, depending on model support. | | | `metadata` | object | None | - | Business metadata. Avoid sensitive data. | | ## Google-compatible parameters Google-native APIs usually put generation parameters in `generationConfig`. Moxus AI also accepts some snake\_case fields, such as `top_p` and `max_output_tokens`. | Parameter | Type | Default | Range | Meaning | | -------------------------------------------------------- | --------------- | ------------- | --------------------------------- | ---------------------------------------------- | | `contents` | array / string | None | - | Main Google-native input. | | `systemInstruction` | object / string | None | - | Google-native system instruction. | | `tools` | array / object | None | - | Tool or search declarations. | | `generationConfig.temperature` | number | Model default | \[0, 2] | Controls randomness. | | `generationConfig.topP` / `top_p` | number | Model default | \[0, 1] | Nucleus sampling. | | `generationConfig.topK` / `top_k` | number | Model default | \[1, +∞) | Candidate token limit. | | `generationConfig.maxOutputTokens` / `max_output_tokens` | integer | Model default | \[0, limit] | Output token cap. | | `generationConfig.candidateCount` | integer | `1` | \[1, +∞) | Number of candidates. | | `generationConfig.stopSequences` | array | None | - | Stop sequences. | | `generationConfig.responseMimeType` | string | None | `application/json` / `text/plain` | Response MIME type. | | `generationConfig.responseSchema` | object | None | - | Structured output schema. | | `generationConfig.presencePenalty` | number | `0` | \[-2, 2] | Topic repetition penalty. | | `generationConfig.frequencyPenalty` | number | `0` | \[-2, 2] | Token frequency penalty. | | `generationConfig.seed` | integer | None | - | Random seed. | | `generationConfig.thinkingConfig` | object | Model default | - | Thinking budget or toggle. | | `generationConfig.responseModalities` | array | Model default | `TEXT` / `IMAGE` | Output modalities, depending on model support. | ## Image generation parameters | Parameter | Type | Default | Range | Meaning | | ------------------------- | --------------- | ------------- | --------------------------------- | -------------------------------------------------- | | `model` | string | None | - | Image generation model. | | `prompt` | string | None | - | Image generation prompt. | | `n` | integer | `1` | \[1, 128] | Number of images. More images cost more. | | `size` | string | Model default | - | Output size. Allowed values depend on model. | | `quality` | string | `auto` | - | Image quality tier, model-dependent. | | `response_format` | string | Model default | `url` / `b64_json` | Image response format. | | `background` | string / object | Model default | `transparent` / `opaque` / `auto` | Background configuration. | | `output_format` | string | Model default | `png` / `jpeg` / `webp` | Output image format. | | `output_compression` | integer | Model default | \[0, 100] | Compression quality, supported by some formats. | | `stream` | boolean | `false` | `true` / `false` | Stream progress or partial images where supported. | | `metadata` / extra fields | object | None | - | Vendor-specific passthrough parameters. | ## Audio parameters | Parameter | Type | Default | Range | Meaning | | ----------------- | ------ | ------------- | ---------------------- | ----------------------------------------- | | `model` | string | None | - | Speech model to call. | | `input` | string | None | - | TTS or audio task input. | | `voice` | string | Model default | - | Voice name, depending on model support. | | `instructions` | string | None | - | Speech generation guidance. | | `response_format` | string | Model default | `mp3` / `wav` / `json` | Response format. | | `speed` | number | `1` | \[0.25, 4] | Speech speed, depending on model support. | | `stream_format` | string | None | `sse` | Streaming audio format. | | `metadata` | object | None | - | Business tracing or vendor extensions. | ## Privacy-related fields | Parameter | Type | Default | Platform behavior | Meaning | | ------------------------------------ | ------- | ---------------- | -------------------------------------------------------------- | --------------------------------------------------------------------------------- | | `store` | boolean | Upstream default | Passed through by default; can be disabled by channel settings | Controls whether upstream may store request or output. | | `safety_identifier` | string | None | Filtered by default unless a channel explicitly allows it | Upstream safety identifier. Use carefully because it may identify users. | | `stream_options.include_obfuscation` | boolean | Upstream default | Filtered by default unless explicitly allowed | Controls streaming obfuscation behavior. | | `metadata` | object | None | May be logged or passed through | Custom metadata. Do not put API keys, passwords, or personal sensitive data here. | ## Recommendations * For a first call, send only `model` plus `messages` or `input`. * If you are unsure, adjust only one sampling parameter first, usually `temperature`. * Set `max_tokens` or `max_output_tokens` when cost or response length matters. * For tool calling, start with a simple schema before adding complex fields. * Do not put API keys, database URLs, identity numbers, or other sensitive data in `metadata` or prompts. ## Related docs * [Quickstart](/en/overview/quickstart) * [Structured output](/en/guide/structured-output) * [Function calling](/en/guide/function-calling) * [Privacy and data](/en/platform/privacy)