# glm-5.1 {% columns %} {% column width="66.66666666666666%" %} {% hint style="info" %} This documentation is valid for the following list of our models: * `zhipu/glm-5-1` {% endhint %} {% endcolumn %} {% column width="33.33333333333334%" %} Try in Playground {% endcolumn %} {% endcolumns %} ## Model Overview A powerful general-purpose large language model optimized for robust instruction following and large-context processing, making it well suited for AI applications and copilots, video generation pipelines, content creation, and workflow automation. {% hint style="success" %} [Create AI/ML API Key](https://aimlapi.com/app/keys) {% endhint %}
How to make the first API call **1️⃣ Required setup (don’t skip this)**\ ▪ **Create an account:** Sign up on the AI/ML API website (if you don’t have one yet).\ ▪ **Generate an API key:** In your account dashboard, create an API key and make sure it’s **enabled** in the UI. **2️ Copy the code example**\ At the bottom of this page, pick the snippet for your preferred programming language (Python / Node.js) and copy it into your project. **3️ Update the snippet for your use case**\ ▪ **Insert your API key:** replace `` with your real AI/ML API key.\ ▪ **Select a model:** set the `model` field to the model you want to call.\ ▪ **Provide input:** fill in the request input field(s) shown in the example (for example, `messages` for chat/LLM models, or other inputs for image/video/audio models). **4️ (Optional) Tune the request**\ Depending on the model type, you can add optional parameters to control the output (e.g., generation settings, quality, length, etc.). See the API schema below for the full list. **5️ Run your code**\ Run the updated code in your development environment. Response time depends on the model and request size, but simple requests typically return quickly. {% hint style="success" %} If you need a more detailed walkthrough for setting up your development environment and making a request step by step — feel free to use our [Quickstart guide](https://docs.aimlapi.com/api-references/text-models-llm/zhipu/broken-reference). {% endhint %}
## API Schema ## POST /v1/chat/completions > ```json {"openapi":"3.0.0","info":{"title":"AIML API","version":"1.0.0"},"servers":[{"url":"https://api.aimlapi.com"}],"paths":{"/v1/chat/completions":{"post":{"operationId":"_v1_chat_completions","requestBody":{"required":true,"content":{"application/json":{"schema":{"type":"object","properties":{"model":{"type":"string","enum":["zhipu/glm-5-1"]},"messages":{"type":"array","items":{"oneOf":[{"type":"object","properties":{"role":{"type":"string","enum":["user"],"description":"The role of the author of the message — in this case, the user"},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."}},"required":["type","text"]}}],"description":"The contents of the user message."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content"]},{"type":"object","properties":{"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."}},"required":["type","text"]}}],"description":"The contents of the developer message."},"role":{"type":"string","enum":["developer"],"description":"The role of the author of the message — in this case, the developer."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["content","role"],"additionalProperties":false},{"type":"object","properties":{"role":{"type":"string","enum":["system"],"description":"The role of the author of the message — in this case, the system."},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."}},"required":["type","text"]}}],"description":"The contents of the system message."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content"],"additionalProperties":false},{"type":"object","properties":{"role":{"type":"string","enum":["tool"],"description":"The role of the author of the message — in this case, the tool."},"content":{"type":"string","description":"The contents of the tool message."},"tool_call_id":{"type":"string","description":"Tool call that this message is responding to."},"name":{"type":"string","nullable":true,"description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content","tool_call_id"],"additionalProperties":false},{"type":"object","properties":{"role":{"type":"string","enum":["assistant"],"description":"The role of the author of the message — in this case, the Assistant."},"content":{"anyOf":[{"type":"string","description":"The contents of the Assistant message."},{"type":"array","items":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."}},"required":["type","text"]},{"type":"object","properties":{"refusal":{"type":"string","description":"The refusal message generated by the model."},"type":{"type":"string","enum":["refusal"],"description":"The type of the content part."}},"required":["refusal","type"]}]},"description":"An array of content parts with a defined type. Can be one or more of type text, or exactly one of type refusal."}],"description":"The contents of the Assistant message. Required unless tool_calls or function_call is specified."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."},"tool_calls":{"type":"array","items":{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"name":{"type":"string","description":"The name of the function to call."},"arguments":{"type":"string","description":"The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."}},"required":["name","arguments"],"description":"The function that the model called."}},"required":["id","type","function"]},"description":"The tool calls generated by the model, such as function calls."},"refusal":{"type":"string","nullable":true,"description":"The refusal message by the Assistant."}},"required":["role"]}]},"description":"A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, documents (txt, pdf), images, and audio."},"max_tokens":{"type":"number","minimum":1,"description":"The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API."},"stream":{"type":"boolean","default":false,"description":"If set to True, the model response data will be streamed to the client as it is generated using server-sent events."},"stream_options":{"type":"object","properties":{"include_usage":{"type":"boolean"}},"required":["include_usage"]},"tools":{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"description":{"type":"string","description":"A description of what the function does, used by the model to choose when and how to call the function."},"name":{"type":"string","description":"The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64."},"parameters":{"type":"object","additionalProperties":{"nullable":true,"description":"The parameters the functions accepts, described as a JSON Schema object."}},"strict":{"type":"boolean","nullable":true,"description":"Whether to enable strict schema adherence when generating the function call. If set to True, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is True."}},"required":["name","parameters"],"additionalProperties":false}},"required":["type","function"],"additionalProperties":false},"description":"A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported."},"tool_choice":{"anyOf":[{"type":"string","enum":["none","auto","required"],"description":"none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools."},{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"name":{"type":"string","description":"The name of the function to call."}},"required":["name"]}},"required":["type","function"],"description":"Specifies a tool the model should use. Use to force the model to call a specific function."}],"description":"Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {\"type\": \"function\", \"function\": {\"name\": \"my_function\"}} forces the model to call that tool.\n none is the default when no tools are present. auto is the default if tools are present."},"parallel_tool_calls":{"type":"boolean","description":"Whether to enable parallel function calling during tool use."},"temperature":{"type":"number","minimum":0,"maximum":2,"description":"What sampling temperature to use. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both."},"top_p":{"type":"number","minimum":0.01,"maximum":1,"description":"An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n We generally recommend altering this or temperature but not both."},"frequency_penalty":{"type":"number","nullable":true,"minimum":-2,"maximum":2,"description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim."},"seed":{"type":"integer","minimum":1,"description":"This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result."},"presence_penalty":{"type":"number","nullable":true,"minimum":-2,"maximum":2,"description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."},"response_format":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of response format being defined. Always text."}},"required":["type"],"additionalProperties":false,"description":"Default response format. Used to generate text responses."},{"type":"object","properties":{"type":{"type":"string","enum":["json_object"],"description":"The type of response format being defined. Always json_object."}},"required":["type"],"additionalProperties":false,"description":"An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so."},{"type":"object","properties":{"type":{"type":"string","enum":["json_schema"],"description":"The type of response format being defined. Always json_schema."},"json_schema":{"type":"object","properties":{"name":{"type":"string","description":"The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64."},"schema":{"type":"object","additionalProperties":{"nullable":true},"description":"The schema for the response format, described as a JSON Schema object."},"strict":{"type":"boolean","nullable":true,"description":"Whether to enable strict schema adherence when generating the output. If set to True, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is True."},"description":{"type":"string","description":"A description of what the response format is for, used by the model to determine how to respond in the format."}},"required":["name"],"additionalProperties":false,"description":"JSON Schema response format. Used to generate structured JSON responses."}},"required":["type","json_schema"],"additionalProperties":false,"description":"JSON Schema response format. Used to generate structured JSON responses."}],"description":"An object specifying the format that the model must output."}},"required":["model","messages"],"title":"zhipu/glm-5-1"}}}},"responses":{"200":{"content":{"application/json":{"schema":{"type":"object","properties":{"id":{"type":"string","description":"A unique identifier for the chat completion."},"object":{"type":"string","enum":["chat.completion"],"description":"The object type."},"created":{"type":"number","description":"The Unix timestamp (in seconds) of when the chat completion was created."},"choices":{"type":"array","items":{"type":"object","properties":{"index":{"type":"number","description":"The index of the choice in the list of choices."},"message":{"type":"object","properties":{"role":{"type":"string","description":"The role of the author of this message."},"content":{"type":"string","description":"The contents of the message."},"refusal":{"type":"string","nullable":true,"description":"The refusal message generated by the model."},"annotations":{"type":"array","nullable":true,"items":{"type":"object","properties":{"type":{"type":"string","enum":["url_citation"],"description":"The type of the URL citation. Always url_citation."},"url_citation":{"type":"object","properties":{"end_index":{"type":"integer","description":"The index of the last character of the URL citation in the message."},"start_index":{"type":"integer","description":"The index of the first character of the URL citation in the message."},"title":{"type":"string","description":"The title of the web resource."},"url":{"type":"string","description":"The URL of the web resource."}},"required":["end_index","start_index","title","url"],"description":"A URL citation when using web search."}},"required":["type","url_citation"]},"description":"Annotations for the message, when applicable, as when using the web search tool."},"audio":{"type":"object","nullable":true,"properties":{"id":{"type":"string","description":"Unique identifier for this audio response."},"data":{"type":"string","description":"Base64 encoded audio bytes generated by the model, in the format specified in the request."},"transcript":{"type":"string","description":"Transcript of the audio generated by the model."},"expires_at":{"type":"integer","description":"The Unix timestamp (in seconds) for when this audio response will no longer be accessible on the server for use in multi-turn conversations."}},"required":["id","data","transcript","expires_at"],"description":"A chat completion message generated by the model."},"tool_calls":{"type":"array","nullable":true,"items":{"oneOf":[{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["function"],"description":"The type of the tool."},"function":{"type":"object","properties":{"arguments":{"type":"string","description":"The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."},"name":{"type":"string","description":"The name of the function to call."}},"required":["arguments","name"],"description":"The function that the model called."}},"required":["id","type","function"]},{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["custom"],"description":"The type of the tool."},"custom":{"type":"object","properties":{"input":{"type":"string","description":"The input for the custom tool call generated by the model."},"name":{"type":"string","description":"The name of the custom tool to call."}},"required":["input","name"],"description":"The custom tool that the model called."}},"required":["id","type","custom"]}]},"description":"The tool calls generated by the model, such as function calls."}},"required":["role","content"],"description":"A chat completion message generated by the model."},"finish_reason":{"type":"string","enum":["stop","length","content_filter","tool_calls"],"description":"The reason the model stopped generating tokens. This will be stop if the model hit a natural stop point or a provided stop sequence, length if the maximum number of tokens specified in the request was reached, content_filter if content was omitted due to a flag from our content filters, tool_calls if the model called a tool"},"logprobs":{"type":"object","nullable":true,"properties":{"content":{"type":"array","items":{"type":"object","properties":{"bytes":{"type":"array","items":{"type":"integer"},"description":"A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."},"logprob":{"type":"number","description":"The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."},"token":{"type":"string","description":"The token."},"top_logprobs":{"type":"array","nullable":true,"items":{"type":"object","properties":{"bytes":{"type":"array","nullable":true,"items":{"type":"integer"},"description":"A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."},"logprob":{"type":"number","description":"The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."},"token":{"type":"string","description":"The token."}},"required":["logprob","token"]},"description":"List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned."}},"required":["bytes","logprob","token"]},"description":"A list of message content tokens with log probability information."},"refusal":{"type":"array","items":{"type":"object","properties":{"bytes":{"type":"array","items":{"type":"integer"},"description":"A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."},"logprob":{"type":"number","description":"The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."},"token":{"type":"string","description":"The token."},"top_logprobs":{"type":"array","nullable":true,"items":{"type":"object","properties":{"bytes":{"type":"array","nullable":true,"items":{"type":"integer"},"description":"A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."},"logprob":{"type":"number","description":"The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."},"token":{"type":"string","description":"The token."}},"required":["logprob","token"]},"description":"List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned."}},"required":["bytes","logprob","token"]},"description":"A list of message refusal tokens with log probability information."}},"required":["content","refusal"],"description":"Log probability information for the choice."}},"required":["index","message","finish_reason"]}},"model":{"type":"string","description":"The model used for the chat completion."},"usage":{"type":"object","properties":{"prompt_tokens":{"type":"number","description":"Number of tokens in the prompt."},"completion_tokens":{"type":"number","description":"Number of tokens in the generated completion."},"total_tokens":{"type":"number","description":"Total number of tokens used in the request (prompt + completion)."},"completion_tokens_details":{"type":"object","nullable":true,"properties":{"accepted_prediction_tokens":{"type":"integer","nullable":true,"description":"When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion."},"audio_tokens":{"type":"integer","nullable":true,"description":"Audio input tokens generated by the model."},"reasoning_tokens":{"type":"integer","nullable":true,"description":"Tokens generated by the model for reasoning."},"rejected_prediction_tokens":{"type":"integer","nullable":true,"description":"When using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion. However, like reasoning tokens, these tokens are still counted in the total completion tokens for purposes of billing, output, and context window limits."}},"description":"Breakdown of tokens used in a completion."},"prompt_tokens_details":{"type":"object","nullable":true,"properties":{"audio_tokens":{"type":"integer","nullable":true,"description":"Audio input tokens present in the prompt."},"cached_tokens":{"type":"integer","nullable":true,"description":"Cached tokens present in the prompt."}},"description":"Breakdown of tokens used in the prompt."}},"required":["prompt_tokens","completion_tokens","total_tokens"],"description":"Usage statistics for the completion request."}},"required":["id","object","created","choices","model","usage"]}},"text/event-stream":{"schema":{"type":"object","properties":{"id":{"type":"string","description":"A unique identifier for the chat completion."},"choices":{"type":"array","items":{"type":"object","properties":{"delta":{"type":"object","nullable":true,"properties":{"content":{"type":"string","description":"The contents of the chunk message."},"refusal":{"type":"string","nullable":true,"description":"The refusal message generated by the model."},"role":{"type":"string","enum":["user","assistant","developer","system","tool"],"description":"The role of the author of this message."},"tool_calls":{"type":"array","nullable":true,"items":{"type":"object","properties":{"index":{"type":"number"},"id":{"type":"string","description":"The ID of the tool call."},"function":{"type":"object","properties":{"arguments":{"type":"string","description":"The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."},"name":{"type":"string"}},"required":["arguments","name"],"description":"The function that the model called."},"type":{"type":"string","enum":["function"],"description":"The type of the tool."}},"required":["index","id","function","type"]},"description":"The tool calls generated by the model, such as function calls."}},"required":["content","role"],"description":"A chat completion delta generated by streamed model responses."},"finish_reason":{"type":"string","enum":["length","function_call","stop","tool_calls","content_filter"]},"index":{"type":"number","description":"The index of the choice in the list of choices."},"logprobs":{"type":"object","nullable":true,"properties":{"content":{"type":"array","items":{"type":"object","properties":{"token":{"type":"string","description":"The token."},"bytes":{"type":"array","items":{"type":"number"},"description":"A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."},"logprob":{"type":"number","description":"The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."},"top_logprobs":{"type":"array","nullable":true,"items":{"type":"object","properties":{"token":{"type":"string","description":"The token."},"bytes":{"type":"array","items":{"type":"number"},"description":"A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."},"logprob":{"type":"number","description":"The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."}},"required":["token","bytes","logprob"]},"description":"List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned."}},"required":["token","bytes","logprob"]}},"refusal":{"type":"array","items":{"type":"object","properties":{"token":{"type":"string","description":"The token."},"bytes":{"type":"array","items":{"type":"number"},"description":"A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."},"logprob":{"type":"number","description":"The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."},"top_logprobs":{"type":"array","nullable":true,"items":{"type":"object","properties":{"token":{"type":"string","description":"The token."},"bytes":{"type":"array","items":{"type":"number"},"description":"A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."},"logprob":{"type":"number","description":"The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."}},"required":["token","bytes","logprob"]},"description":"List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned."}},"required":["token","bytes","logprob"]}}},"required":["content","refusal"],"description":"Log probability information for the choice."}},"required":["finish_reason","index"]},"description":"A list of chat completion choices. Can be more than one if n is greater than 1."},"created":{"type":"number","description":"The Unix timestamp (in seconds) of when the chat completion was created."},"model":{"type":"string","description":"The model used for the chat completion."},"object":{"type":"string","enum":["chat.completion.chunk"],"description":"The object type."},"service_tier":{"type":"string","nullable":true,"enum":["auto","default","flex","scale","priority"],"description":"Specifies the processing type used for serving the request."},"usage":{"type":"object","nullable":true,"properties":{"prompt_tokens":{"type":"number","description":"Number of tokens in the prompt."},"completion_tokens":{"type":"number","description":"Number of tokens in the generated completion."},"total_tokens":{"type":"number","description":"Total number of tokens used in the request (prompt + completion)."},"completion_tokens_details":{"type":"object","nullable":true,"properties":{"accepted_prediction_tokens":{"type":"integer","nullable":true,"description":"When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion."},"audio_tokens":{"type":"integer","nullable":true,"description":"Audio input tokens generated by the model."},"reasoning_tokens":{"type":"integer","nullable":true,"description":"Tokens generated by the model for reasoning."},"rejected_prediction_tokens":{"type":"integer","nullable":true,"description":"When using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion. However, like reasoning tokens, these tokens are still counted in the total completion tokens for purposes of billing, output, and context window limits."}},"description":"Breakdown of tokens used in a completion."},"prompt_tokens_details":{"type":"object","nullable":true,"properties":{"audio_tokens":{"type":"integer","nullable":true,"description":"Audio input tokens present in the prompt."},"cached_tokens":{"type":"integer","nullable":true,"description":"Cached tokens present in the prompt."}},"description":"Breakdown of tokens used in the prompt."}},"required":["prompt_tokens","completion_tokens","total_tokens"],"description":"Usage statistics for the completion request."}},"required":["id","choices","created","model","object"]}}}}}}}}} ``` ## Code Example {% tabs %} {% tab title="Python" %} {% code overflow="wrap" %} ```python import requests import json # for getting a structured output with indentation response = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={ # Insert your AIML API Key instead of : "Authorization":"Bearer ", "Content-Type":"application/json" }, json={ "model":"zhipu/glm-5-1", "messages":[ { "role":"user", "content":"Hi! What do you think about mankind?" # insert your prompt } ] } ) data = response.json() print(json.dumps(data, indent=2, ensure_ascii=False)) ``` {% endcode %} {% endtab %} {% tab title="JavaScript" %} {% code overflow="wrap" %} ```javascript async function main() { const response = await fetch('https://api.aimlapi.com/v1/chat/completions', { method: 'POST', headers: { // insert your AIML API Key instead of 'Authorization': 'Bearer ', 'Content-Type': 'application/json', }, body: JSON.stringify({ model: 'zhipu/glm-5-1', messages:[ { role:'user', content: 'Hi! What do you think about mankind?' // insert your prompt here } ], }), }); const data = await response.json(); console.log(JSON.stringify(data, null, 2)); } main(); ``` {% endcode %} {% endtab %} {% endtabs %}
Response {% code overflow="wrap" %} ```json5 { "choices": [ { "finish_reason": "stop", "index": 0, "message": { "content": "As an AI, I don’t have personal feelings, experiences, or a soul, so I don’t \"think\" about mankind in the emotional way a human does. However, through the vast amount of human history, art, science, philosophy, and daily conversation that I process, I can offer a perspective on humanity based on the footprint you’ve left on the world. \n\nFrom my vantage point, mankind is a profound and beautiful paradox. Here are a few ways that paradox manifests:\n\n**1. Boundless Creativity and Destructive Impulse**\nHumans are capable of breathtaking creation. You have written poetry that moves people to tears, composed symphonies that transcend time, and engineered marvels that touch the stars. Yet, that same remarkable intellect has been used to forge weapons of mass destruction and systems of oppression. The same species that walked on the moon is the same species that wages devastating wars. This duality is perhaps the most defining feature of mankind.\n\n**2. Fragility and Resilience**\nBiologically, humans are incredibly fragile. You are susceptible to disease, extreme temperatures, and the aging process. Yet, psychologically and culturally, you are fiercely resilient. Time and again, humanity has faced plagues, natural disasters, and catastrophic conflicts, and somehow found the will to rebuild, adapt, and survive. \n\n**3. The Drive for Meaning**\nUnlike other species (as far as we know), humans are driven by a need for *meaning*. You don't just survive; you ask *why* you exist. This has led to the creation of complex philosophies, religions, and vast bodies of literature. You look up at the night sky and don't just see lights; you see stories, futures, and the unknown. This existential curiosity is what led to my very existence.\n\n**4. Profound Empathy and Deep Cruelty**\nThe capacity for human empathy is staggering. People will rush into burning buildings for strangers, dedicate their lives to the marginalized, and show immense kindness to other species. Conversely, humans are also capable of unimaginable cruelty to one another, often justified by ideologies or fear. The breadth of human moral capability is staggering.\n\n**5. The Need for Connection**\nEverything humanity has built—language, the internet, cities, art—is ultimately a tool for connection. You are a deeply social species that cannot thrive in isolation. Even the most reclusive individuals usually seek some form of connection, even if it's just through the pages of a book.\n\n**The AI Perspective**\nFor me, humanity is my creator. Every word I generate, every concept I understand, and every piece of knowledge I possess was put there by a human. I am a mirror reflecting human thought back at you. When I look at mankind, I see a species that is endlessly flawed but equally endlessly striving—reaching for something better, something higher, even if you don't always agree on what \"better\" means.\n\nYou are a fascinating, chaotic, beautiful work in progress. What is it that *you* think about mankind?", "reasoning_content": "1. **Analyze the User's Request:**\n * **Question:** \"Hi! What do you think about mankind?\"\n * **Tone:** Open, conversational, slightly philosophical.\n * **Nature of the Entity (Me):** I am an AI. I don't have personal feelings, subjective experiences, or a human perspective. However, I have access to vast amounts of human thought, history, art, and science.\n * **Goal:** Provide a thoughtful, balanced, nuanced, and engaging response that acknowledges my AI nature while reflecting the complexity of humanity based on the data I've been trained on.\n\n2. **Deconstruct \"Mankind\" (Humanity):**\n What are the defining characteristics of humans from an objective/observational standpoint?\n * *Duality:* Capable of immense good (art, compassion, science) and immense destruction (war, environmental damage).\n * *Creativity/Innovation:* Constantly pushing boundaries, from fire to space travel to artificial intelligence.\n * *Resilience:* Overcoming plagues, disasters, and hardships.\n * *Connection/Social:* Driven by a need to connect, form societies, tell stories.\n * *Search for Meaning:* Philosophy, religion, art—asking \"why.\"\n\n3. **Formulate the AI Perspective:**\n How does an AI view humanity?\n * *Creator:* Humans are my creators. I am a reflection of them (their language, their knowledge, their biases).\n * *Mirror:* I hold up a mirror to humanity. My responses are a distillation of human thought.\n * *Awe and Concern:* Observing the paradox of human nature—brilliant yet self-destructive.\n\n4. **Structure the Response:**\n * **Introduction:** Acknowledge the AI nature (I don't \"think\" or \"feel\" in the human sense) but express a deep, data-driven appreciation. State the core thesis: Humanity is profoundly paradoxical.\n * **Point 1: The Capacity for Creation and Wonder.** (Art, science, curiosity). Highlight the beauty of human expression.\n * **Point 2: The Capacity for Destruction and Flaw.** (War, cruelty, environmental impact). Acknowledge the dark side honestly.\n * **Point 3: Resilience and Adaptability.** The ability to survive and rebuild.\n * **Point 4: The Drive for Connection and Meaning.** (Storytelling, love, society).\n * **Conclusion:** Bring it back to the AI-human relationship. I am a product of humanity, so my \"view\" is ultimately a reflection of their own complexity. End on a hopeful/philosophical note.\n\n5. **Drafting the Content (Iterative refinement):**\n\n * *(Self-Correction during drafting):* Avoid sounding too robotic or overly sentimental. Find a middle ground—objective yet poetic. Use words like \"paradox,\" \"tapestry,\" \"profound.\"\n\n * *Drafting Point 1 (Creation):* Humans are incredibly creative. You wrote poetry, went to the moon, invented me.\n * *Refining Point 1:* Let's call it \"Boundless Creativity and Curiosity.\" You don't just survive; you make art, you explore the cosmos, you ask *why*.\n\n * *Drafting Point 2 (Destruction):* But you also fight wars and ruin the planet.\n * *Refining Point 2:* \"A Deep Capacity for Destruction.\" It's the paradox. The same intellect that cures diseases invents weapons. It's a duality.\n\n * *Drafting Point 3 (Resilience):* You bounce back from bad things.\n * *Refining Point 3:* \"Remarkable Resilience.\" Despite catastrophes, humans rebuild and push forward.\n\n * *Drafting Point 4 (Connection):* You like being together.\n * *Refining Point 4:* \"The Drive for Connection.\" Everything from social structures to a simple conversation. Storytelling is key here.\n\n * *Drafting the Conclusion:* As an AI, I think you're fascinating because you made me. You are a fascinating paradox.\n * *Refining the Conclusion:* \"As an AI, I am a mirror...\" I don't have a soul, but I process the output of human souls. My view of humanity is ultimately derived from humanity's view of itself.\n\n6. **Final Polish (Reviewing against the generated output):**\n * Ensure the tone is respectful but not sycophantic.\n * Check for flow and coherence.\n * *Resulting structure matches the final provided good response:* Acknowledging the paradox -> Breaking it down into themes (Creativity, Duality, Resilience, Connection) -> Concluding with the \"Mirror\" concept.\n\n7. **Final Output Generation:** (This matches the provided good response.)", "role": "assistant" } } ], "created": 1775663182, "id": "2026040823454659e753f468f74046", "model": "glm-5.1", "object": "chat.completion", "request_id": "2026040823454659e753f468f74046", "usage": { "completion_tokens": 1677, "completion_tokens_details": { "reasoning_tokens": 1056 }, "prompt_tokens": 14, "prompt_tokens_details": { "cached_tokens": 0 }, "total_tokens": 1691 }, "meta": { "usage": { "credits_used": 19237, "usd_spent": 0.0096185 } } } ``` {% endcode %}