# Create public — POST /v1/chat/public URL: https://docs.hanzo.ai/docs/openapi/ai/post-chat-public > Serves one completion to a caller with no account. `POST /v1/chat/public` > [AI →](https://docs.hanzo.ai/docs/openapi/ai) · [All API references →](https://docs.hanzo.ai/docs/openapi) · [Get started →](https://docs.hanzo.ai/docs/guides) | | | | ------------- | -------------------------------------- | | **Address** | `https://api.hanzo.ai/v1/chat/public` | | **Method** | `POST` | | **Operation** | `post_chat_public` | | **Auth** | `Authorization: Bearer $HANZO_API_KEY` | Serves one completion to a caller with no account. ## Request 67 fields, body `application/json` (required). | Field | In | Type | Required | Description | | -------------------------------------------- | ---- | --------------------------------------------- | -------- | ----------- | | `frequency_penalty` | body | number | — | | | `function_call` | body | any | — | | | `functions` | body | openai.FunctionDefinition\[] | — | | | `functions[].description` | body | string | — | | | `functions[].name` | body | string | — | | | `functions[].parameters` | body | any | — | | | `functions[].strict` | body | boolean | — | | | `logit_bias` | body | object | — | | | `logit_bias.*` | body | integer | — | | | `logprobs` | body | boolean | — | | | `max_completion_tokens` | body | integer | — | | | `max_tokens` | body | integer | — | | | `messages` | body | openai.ChatCompletionMessage\[] | — | | | `messages[].MultiContent` | body | openai.ChatMessagePart\[] | — | | | `messages[].MultiContent[].image_url` | body | openai.ChatMessageImageURL | — | | | `messages[].MultiContent[].image_url.detail` | body | string | — | | | `messages[].MultiContent[].image_url.url` | body | string | — | | | `messages[].MultiContent[].text` | body | string | — | | | `messages[].MultiContent[].type` | body | string | — | | | `messages[].content` | body | string | — | | | `messages[].function_call` | body | openai.FunctionCall | — | | | `messages[].function_call.arguments` | body | string | — | | | `messages[].function_call.name` | body | string | — | | | `messages[].name` | body | string | — | | | `messages[].reasoning_content` | body | string | — | | | `messages[].refusal` | body | string | — | | | `messages[].role` | body | string | — | | | `messages[].tool_call_id` | body | string | — | | | `messages[].tool_calls` | body | openai.ToolCall\[] | — | | | `messages[].tool_calls[].function` | body | openai.FunctionCall | — | | | `messages[].tool_calls[].function.arguments` | body | string | — | | | `messages[].tool_calls[].function.name` | body | string | — | | | `messages[].tool_calls[].id` | body | string | — | | | `messages[].tool_calls[].index` | body | integer | — | | | `messages[].tool_calls[].type` | body | string | — | | | `metadata` | body | object | — | | | `metadata.*` | body | string | — | | | `model` | body | string | — | | | `n` | body | integer | — | | | `parallel_tool_calls` | body | any | — | | | `presence_penalty` | body | number | — | | | `reasoning_effort` | body | string | — | | | `response_format` | body | openai.ChatCompletionResponseFormat | — | | | `response_format.json_schema` | body | openai.ChatCompletionResponseFormatJSONSchema | — | | | `response_format.json_schema.description` | body | string | — | | | `response_format.json_schema.name` | body | string | — | | | `response_format.json_schema.schema` | body | any | — | | | `response_format.json_schema.strict` | body | boolean | — | | | `response_format.type` | body | string | — | | | `seed` | body | integer | — | | | `stop` | body | string\[] | — | | | `store` | body | boolean | — | | | `stream` | body | boolean | — | | | `stream_options` | body | openai.StreamOptions | — | | | `stream_options.include_usage` | body | boolean | — | | | `temperature` | body | number | — | | | `tool_choice` | body | any | — | | | `tools` | body | openai.Tool\[] | — | | | `tools[].function` | body | openai.FunctionDefinition | — | | | `tools[].function.description` | body | string | — | | | `tools[].function.name` | body | string | — | | | `tools[].function.parameters` | body | any | — | | | `tools[].function.strict` | body | boolean | — | | | `tools[].type` | body | string | — | | | `top_logprobs` | body | integer | — | | | `top_p` | body | number | — | | | `user` | body | string | — | | ## Response | Status | Body | Meaning | | ------ | ----------------------------- | --------------------------------------------------- | | `200` | openai.ChatCompletionResponse | Success. | | `401` | — | No credential, or one this service does not accept. | | `403` | — | A valid credential that may not do this. | `200` body — 90 fields. | Field | In | Type | Always | Description | | ------------------------------------------------------------------- | ---- | ------------------------------ | ------ | ----------- | | `choices` | body | openai.ChatCompletionChoice\[] | — | | | `choices[].content_filter_results` | body | openai.ContentFilterResults | — | | | `choices[].content_filter_results.hate` | body | openai.Hate | — | | | `choices[].content_filter_results.hate.filtered` | body | boolean | — | | | `choices[].content_filter_results.hate.severity` | body | string | — | | | `choices[].content_filter_results.jailbreak` | body | openai.JailBreak | — | | | `choices[].content_filter_results.jailbreak.detected` | body | boolean | — | | | `choices[].content_filter_results.jailbreak.filtered` | body | boolean | — | | | `choices[].content_filter_results.profanity` | body | openai.Profanity | — | | | `choices[].content_filter_results.profanity.detected` | body | boolean | — | | | `choices[].content_filter_results.profanity.filtered` | body | boolean | — | | | `choices[].content_filter_results.self_harm` | body | openai.SelfHarm | — | | | `choices[].content_filter_results.self_harm.filtered` | body | boolean | — | | | `choices[].content_filter_results.self_harm.severity` | body | string | — | | | `choices[].content_filter_results.sexual` | body | openai.Sexual | — | | | `choices[].content_filter_results.sexual.filtered` | body | boolean | — | | | `choices[].content_filter_results.sexual.severity` | body | string | — | | | `choices[].content_filter_results.violence` | body | openai.Violence | — | | | `choices[].content_filter_results.violence.filtered` | body | boolean | — | | | `choices[].content_filter_results.violence.severity` | body | string | — | | | `choices[].finish_reason` | body | string | — | | | `choices[].index` | body | integer | — | | | `choices[].logprobs` | body | openai.LogProbs | — | | | `choices[].logprobs.content` | body | openai.LogProb\[] | — | | | `choices[].logprobs.content[].bytes` | body | string (byte) | — | | | `choices[].logprobs.content[].logprob` | body | number | — | | | `choices[].logprobs.content[].token` | body | string | — | | | `choices[].logprobs.content[].top_logprobs` | body | openai.TopLogProbs\[] | — | | | `choices[].logprobs.content[].top_logprobs[].bytes` | body | string (byte) | — | | | `choices[].logprobs.content[].top_logprobs[].logprob` | body | number | — | | | `choices[].logprobs.content[].top_logprobs[].token` | body | string | — | | | `choices[].message` | body | openai.ChatCompletionMessage | — | | | `choices[].message.MultiContent` | body | openai.ChatMessagePart\[] | — | | | `choices[].message.MultiContent[].image_url` | body | openai.ChatMessageImageURL | — | | | `choices[].message.MultiContent[].image_url.detail` | body | string | — | | | `choices[].message.MultiContent[].image_url.url` | body | string | — | | | `choices[].message.MultiContent[].text` | body | string | — | | | `choices[].message.MultiContent[].type` | body | string | — | | | `choices[].message.content` | body | string | — | | | `choices[].message.function_call` | body | openai.FunctionCall | — | | | `choices[].message.function_call.arguments` | body | string | — | | | `choices[].message.function_call.name` | body | string | — | | | `choices[].message.name` | body | string | — | | | `choices[].message.reasoning_content` | body | string | — | | | `choices[].message.refusal` | body | string | — | | | `choices[].message.role` | body | string | — | | | `choices[].message.tool_call_id` | body | string | — | | | `choices[].message.tool_calls` | body | openai.ToolCall\[] | — | | | `choices[].message.tool_calls[].function` | body | openai.FunctionCall | — | | | `choices[].message.tool_calls[].function.arguments` | body | string | — | | | `choices[].message.tool_calls[].function.name` | body | string | — | | | `choices[].message.tool_calls[].id` | body | string | — | | | `choices[].message.tool_calls[].index` | body | integer | — | | | `choices[].message.tool_calls[].type` | body | string | — | | | `created` | body | integer | — | | | `id` | body | string | — | | | `model` | body | string | — | | | `object` | body | string | — | | | `prompt_filter_results` | body | openai.PromptFilterResult\[] | — | | | `prompt_filter_results[].content_filter_results` | body | openai.ContentFilterResults | — | | | `prompt_filter_results[].content_filter_results.hate` | body | openai.Hate | — | | | `prompt_filter_results[].content_filter_results.hate.filtered` | body | boolean | — | | | `prompt_filter_results[].content_filter_results.hate.severity` | body | string | — | | | `prompt_filter_results[].content_filter_results.jailbreak` | body | openai.JailBreak | — | | | `prompt_filter_results[].content_filter_results.jailbreak.detected` | body | boolean | — | | | `prompt_filter_results[].content_filter_results.jailbreak.filtered` | body | boolean | — | | | `prompt_filter_results[].content_filter_results.profanity` | body | openai.Profanity | — | | | `prompt_filter_results[].content_filter_results.profanity.detected` | body | boolean | — | | | `prompt_filter_results[].content_filter_results.profanity.filtered` | body | boolean | — | | | `prompt_filter_results[].content_filter_results.self_harm` | body | openai.SelfHarm | — | | | `prompt_filter_results[].content_filter_results.self_harm.filtered` | body | boolean | — | | | `prompt_filter_results[].content_filter_results.self_harm.severity` | body | string | — | | | `prompt_filter_results[].content_filter_results.sexual` | body | openai.Sexual | — | | | `prompt_filter_results[].content_filter_results.sexual.filtered` | body | boolean | — | | | `prompt_filter_results[].content_filter_results.sexual.severity` | body | string | — | | | `prompt_filter_results[].content_filter_results.violence` | body | openai.Violence | — | | | `prompt_filter_results[].content_filter_results.violence.filtered` | body | boolean | — | | | `prompt_filter_results[].content_filter_results.violence.severity` | body | string | — | | | `prompt_filter_results[].index` | body | integer | — | | | `system_fingerprint` | body | string | — | | | `usage` | body | openai.Usage | — | | | `usage.completion_tokens` | body | integer | — | | | `usage.completion_tokens_details` | body | openai.CompletionTokensDetails | — | | | `usage.completion_tokens_details.audio_tokens` | body | integer | — | | | `usage.completion_tokens_details.reasoning_tokens` | body | integer | — | | | `usage.prompt_tokens` | body | integer | — | | | `usage.prompt_tokens_details` | body | openai.PromptTokensDetails | — | | | `usage.prompt_tokens_details.audio_tokens` | body | integer | — | | | `usage.prompt_tokens_details.cached_tokens` | body | integer | — | | | `usage.total_tokens` | body | integer | — | | Failure carries the platform error shape — see [Errors](https://docs.hanzo.ai/docs/errors). ## Examples **CLI** ```bash hanzo chat public ``` **SDK** **.ts** ```ts import { Configuration, AiApi } from 'hanzoai'; const api = new AiApi(new Configuration({ accessToken: process.env.HANZO_API_KEY })); const { data } = await api.postChatPublic({ frequency_penalty: 0, function_call: "" }); ``` **.py** ```python from hanzoai.cloud import ApiClient, Configuration from hanzoai.cloud.api import AiApi client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"])) result = AiApi(client).post_chat_public(frequency_penalty=0, function_call="") ``` **.go** ```go cfg := hanzoai.NewConfiguration() cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY")) client := hanzoai.NewAPIClient(cfg) resp, _, err := client.AiAPI.PostChatPublic(context.Background()).Execute() if err != nil { return err } ``` **.rs** ```rust use hanzo_client::apis::{configuration::Configuration, ai_api}; let mut cfg = Configuration::new(); cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok(); let result = ai_api::post_chat_public(&cfg, Default::default()).await?; ``` **.java** ```java import ai.hanzo.cloud.ApiClient; import ai.hanzo.cloud.api.AiApi; ApiClient client = new ApiClient(); client.setBearerToken(System.getenv("HANZO_API_KEY")); var result = new AiApi(client).postChatPublic(); ``` **HTTP** ```bash curl -X POST https://api.hanzo.ai/v1/chat/public \ -H "Authorization: Bearer $HANZO_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "frequency_penalty": 0, "function_call": "" }' ``` **MCP** MCP declares no tool for **ai** — `tools/list` on `https://api.hanzo.ai/v1/mcp` names the products it does reach. Use HTTP or an SDK. --- [AI API](https://docs.hanzo.ai/docs/openapi/ai) · [All Hanzo APIs](https://docs.hanzo.ai/docs/openapi) · [Interactive reference](https://docs.hanzo.ai/docs/openapi/reference)