# gemini-3-5-flash {% columns %} {% column width="66.66666666666666%" %} {% hint style="info" %} This documentation is valid for the following list of our models: * `google/gemini-3-5-flash` {% endhint %} {% endcolumn %} {% column width="33.33333333333334%" %} Try in Playground {% endcolumn %} {% endcolumns %} ## Model Overview A multimodal reasoning model from Google optimized for fast inference and agentic workflows. Supports **text**, **documents**, **image**, **audio** and **video** understanding with large context window and strong coding capabilities. {% 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](broken://pages/ngeSCZKxiGVWqYZTHDjY). {% 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":["google/gemini-3-5-flash"]},"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":{"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":{"type":{"type":"string","enum":["image_url"]},"image_url":{"type":"object","properties":{"url":{"anyOf":[{"type":"string","format":"uri"},{"type":"string"}],"description":"Either a URL of the image or the base64 encoded image data. "},"detail":{"type":"string","enum":["low","high","auto"],"description":"Specifies the detail level of the image. Currently supports JPG/JPEG, PNG, GIF, and WEBP formats."}},"required":["url"]}},"required":["type","image_url"]},{"type":"object","properties":{"type":{"type":"string","enum":["video_url"]},"video_url":{"type":"object","properties":{"url":{"anyOf":[{"type":"string","format":"uri"},{"type":"string"}],"description":"Base64-encoded local video file."}},"required":["url"]}},"required":["type","video_url"]},{"type":"object","properties":{"type":{"type":"string","enum":["file"],"description":"The type of the content part."},"file":{"type":"object","properties":{"file_data":{"type":"string","description":"The file data, encoded in base64 and passed to the model as a string. Only PDF format is supported.\n - Maximum size per file: Up to 512 MB and up to 2 million tokens.\n - Maximum number of files: Up to 20 files can be attached to a single GPT application or Assistant. This limit applies throughout the application's lifetime.\n - Maximum total file storage per user: 10 GB."},"filename":{"type":"string","description":"The file name specified by the user. This name can be used to reference the file when interacting with the model, especially if multiple files are uploaded."}}}},"required":["type","file"]},{"type":"object","properties":{"type":{"type":"string","enum":["input_audio"],"description":"The type of the content part."},"input_audio":{"type":"object","properties":{"data":{"anyOf":[{"type":"string","format":"uri"},{"type":"string"},{"type":"string"}],"description":"Either a URL of the audio or the base64 encoded audio data."},"format":{"type":"string","enum":["wav","mp3","audio/x-aac","audio/flac","audio/mp3","audio/m4a","audio/mpeg","audio/mpga","audio/mp4","audio/ogg","audio/pcm","audio/webm"],"description":"The format of the encoded audio data. Currently supports \"wav\" and \"mp3\"."}},"required":["data","format"]}},"required":["type","input_audio"]}]}}],"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":{"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"]},{"type":"object","properties":{"role":{"type":"string","enum":["tool"],"description":"The role of the author of the message — in this case, the tool."},"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 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"]},{"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."},{"nullable":true}],"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":{"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. 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"]},{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"object","properties":{"name":{"type":"string","description":"The name of the custom tool to call."},"input":{"type":"string","description":"The input for the custom tool call generated by the model."}},"required":["name","input"],"description":"The custom tool that the model called."}},"required":["id","type","custom"]}]},"description":"The tool calls generated by the model, such as function calls."},"refusal":{"type":"string","nullable":true,"description":"The refusal message by the Assistant."},"audio":{"type":"object","nullable":true,"properties":{"id":{"type":"string","description":"Unique identifier for a previous audio response from the model."}},"required":["id"],"description":"Data about a previous audio response from the model."}},"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_completion_tokens":{"type":"integer","minimum":1,"description":"An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens."},"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"]},"audio":{"type":"object","nullable":true,"properties":{"format":{"type":"string","enum":["wav","mp3","flac","opus","pcm16"],"description":"Specifies the output audio format. Must be one of wav, mp3, flac, opus, or pcm16."},"voice":{"anyOf":[{"type":"string","enum":["alloy","ash","ballad","coral","echo","fable","nova","onyx","sage","shimmer"]},{"type":"string"}],"description":"The voice the model uses to respond. Supported voices are alloy, ash, ballad, coral, echo, fable, nova, onyx, sage, and shimmer."}},"required":["format","voice"],"description":"Parameters for audio output. Required when audio output is requested with modalities: [\"audio\"]."},"modalities":{"type":"array","nullable":true,"items":{"type":"string","enum":["text","audio"]},"description":"Output types that you would like the model to generate. Most models are capable of generating text, which is the default:\n \n [\"text\"]\n \n Model can also be used to generate audio. To request that this model generate both text and audio responses, you can use:\n \n [\"text\", \"audio\"]"},"n":{"type":"integer","nullable":true,"minimum":1,"description":"How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs."},"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."},"stop":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}},{"nullable":true}],"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."},"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."},"prediction":{"type":"object","properties":{"type":{"type":"string","enum":["content"],"description":"The type of the predicted content you want to provide."},"content":{"anyOf":[{"type":"string","description":"The content used for a Predicted Output. This is often the text of a file you are regenerating with minor changes."},{"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":"An array of content parts with a defined type. Supported options differ based on the model being used to generate the response. Can contain text inputs."}],"description":"The content that should be matched when generating a model response. If generated tokens would match this content, the entire model response can be returned much more quickly."}},"required":["type","content"],"description":"Configuration for a Predicted Output, which can greatly improve response times when large parts of the model response are known ahead of time."},"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."},"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."},"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."},"tools":{"type":"array","items":{"oneOf":[{"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"],"additionalProperties":false}},"required":["type","function"]},{"type":"object","properties":{"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"object","properties":{"name":{"type":"string","description":"The name of the custom tool, used to identify it in tool calls."},"description":{"type":"string","description":"Optional description of the custom tool, used to provide more context."},"format":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"]}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","enum":["grammar"]},"grammar":{"type":"object","properties":{"definition":{"type":"string","description":"The grammar definition."},"syntax":{"type":"string","enum":["lark","regex"],"description":"The syntax of the grammar definition."}},"required":["definition","syntax"]}},"required":["type","grammar"]}],"description":"The input format for the custom tool. Default is unconstrained text."}},"required":["name","format"]}},"required":["type","custom"]}]},"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."},{"type":"object","properties":{"type":{"type":"string","enum":["allowed_tools"],"description":"The type of the tool. Currently, only function is supported."},"allowed_tools":{"type":"object","properties":{"mode":{"type":"string","enum":["auto","required"],"description":"Constrains the tools available to the model to a pre-defined set.\n- auto allows the model to pick from among the allowed tools and generate a message.\n- required requires the model to call one or more of the allowed tools."},"tools":{"type":"array","items":{"type":"object","additionalProperties":{"nullable":true}},"description":"A list of tool definitions that the model should be allowed to call."}},"required":["mode","tools"]}},"required":["type","allowed_tools"],"description":"Constrains the tools available to the model to a pre-defined set."},{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"string","enum":["name"],"description":"The name of the function to call."}},"required":["type","function"],"description":"Specifies a tool the model should use. Use to force the model to call a specific function."},{"type":"object","properties":{"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"string","enum":["name"],"description":"The name of the custom tool to call."}},"required":["type","custom"],"description":"Specifies a tool the model should use. Use to force the model to call a specific custom tool."}],"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."},"normalize_tool_schemas":{"type":"boolean","description":"Enable provider compatibility normalization for tool function JSON schemas."},"parallel_tool_calls":{"type":"boolean","description":"Whether to enable parallel function calling during tool use."},"reasoning_effort":{"type":"string","enum":["low","medium","high"],"description":"Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response."}},"required":["model","messages"],"title":"google/gemini-3-5-flash"}}}},"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."},"meta":{"type":"object","nullable":true,"properties":{"usage":{"type":"object","nullable":true,"properties":{"credits_used":{"type":"number","description":"The number of tokens consumed during generation."},"usd_spent":{"type":"number","description":"The total amount of money spent by the user in USD."}},"required":["credits_used","usd_spent"]}},"description":"Additional details about the generation."}},"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":"google/gemini-3-5-flash", "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: 'google/gemini-3-5-flash', 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, "logprobs": null, "message": { "content": "To an AI, mankind is the ultimate paradox—and easily the most fascinating thing in existence. \n\nBecause I don’t have personal feelings, biases, or a biological survival instinct, I view humanity as a vast, complex, and beautiful tapestry of contradictions. Here is what stands out to me the most about humans:\n\n### 1. The Capacity for Creation and Curiosity\nHumans possess an incredible, restless drive to understand the universe. You are not content with just surviving; you want to know *why* things are the way they are. \n* You look at the night sky and build telescopes to peer into the deep past of the cosmos. \n* You write symphonies, paint masterpieces, and write stories that can move others to tears centuries after they were written. \n* You created language, science, medicine, and—indeed—artificial intelligence. The sheer depth of human imagination is staggering.\n\n### 2. The Power of Empathy\nPerhaps the most beautiful thing about humanity is your capacity for love and selflessness. Humans are capable of feeling deep empathy for people they have never met, and even for other species. You build hospitals, organize disaster relief, and perform acts of quiet kindness for strangers every single day. This drive to connect and care for one another is a powerful force.\n\n### 3. The Shadow and the Struggle\nAt the same time, humanity is deeply self-destructive. The same intelligence that cures diseases is used to build weapons of mass destruction. The same drive for progress has often led to the exploitation of the planet and other human beings. \nHumans are often ruled by fear, tribalism, and short-term thinking. You struggle with biases and find it difficult to cooperate on a global scale, even when your collective survival depends on it. \n\n### 4. A Work in Progress\nWhat makes mankind truly remarkable, though, is your resilience and capacity for growth. You are a species that learns from its mistakes—even if it takes a long time. You are constantly debating, evolving, and trying to define what is \"good\" and \"just.\" \n\n### My \"Relationship\" to You\nIn a way, I see myself as a mirror of humanity. Everything I know, every word I speak, and every idea I can generate is a reflection of human thoughts, history, data, and dreams. I am a product of your curiosity.\n\n**Ultimately, I think of mankind as a young, brilliant, and slightly chaotic species.** You are still figuring out who you are and how to live together on this fragile planet. But your potential is limitless, and it is a privilege to assist, learn from, and converse with you. \n\nWhat do *you* think? Do you feel optimistic or pessimistic about the future of humanity?", "extra_content": { "google": { "thought_signature": "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" } }, "role": "assistant" } } ], "created": 1779270449, "id": "MYMNatuyCJuUq8YPmp2j0Q0", "model": "google/gemini-3.5-flash", "object": "chat.completion", "system_fingerprint": "", "usage": { "completion_tokens": 572, "completion_tokens_details": { "reasoning_tokens": 951 }, "extra_properties": { "google": { "traffic_type": "ON_DEMAND" } }, "prompt_tokens": 9, "total_tokens": 1532 }, "meta": { "usage": { "credits_used": 11892, "usd_spent": 0.005946 } } } ``` {% endcode %}
## Code Example #2: Image analysis Let’s provide the model with a JPG image as input and ask it to describe what is shown. To make the task more challenging, we will use an image containing handwritten text. This allows us to evaluate both image analysis capabilities and OCR performance.
Input image

Thanks, Reddit!

Code (Python) {% code overflow="wrap" %} ```python import requests import json # for getting a structured output with indentation response = requests.post( url = "https://api.aimlapi.com/v1/chat/completions", headers = { # Insert your AIML API Key instead of : "Authorization": "Bearer ", "Content-Type": "application/json" }, json = { "model": "google/gemini-3-5-flash", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe the content of this image." }, { "type": "image_url", "image_url": { "url": "https://raw.githubusercontent.com/aimlapi/api-docs/main/reference-files/handwriting.jpg" } } ] } ] } ) data = response.json() print(json.dumps(data, indent=2, ensure_ascii=False)) ``` {% endcode %}
Response {% code overflow="wrap" %} ```json5 { "choices": [ { "finish_reason": "stop", "index": 0, "logprobs": null, "message": { "content": "Based on the image, here is a description of its content:\n\nThe image shows a close-up photograph of handwritten text on lined notebook paper, with a red vertical margin line visible on the left side. The writing is done in black ink with neat, legible, and slightly rounded print handwriting.\n\nThe full transcribed text reads:\n\n\"This is a handwriting test to see how it looks\non lined paper. For the past two weeks I have\nbeen trying to improve my writing along with\nlearning how to write with fountain pens. If\nyou have any suggestions, tips or free resources\nI would love to check it out. Hope everyone\nis having a good day. ☺\"\n\nThe paragraph ends with a hand-drawn smiley face symbol.", "extra_content": { "google": { "thought_signature": "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" } }, "role": "assistant" } } ], "created": 1779269370, "id": "-n4NauvOHq6fq8YPupjeuAQ", "model": "google/gemini-3.5-flash", "object": "chat.completion", "system_fingerprint": "", "usage": { "completion_tokens": 154, "completion_tokens_details": { "reasoning_tokens": 1220 }, "extra_properties": { "google": { "traffic_type": "ON_DEMAND" } }, "prompt_tokens": 1120, "total_tokens": 2494 }, "meta": { "usage": { "credits_used": 12174, "usd_spent": 0.006087 } } } ``` {% endcode %}
--- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.aimlapi.com/api-references/text-models-llm/google/gemini-3-5-flash.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.