> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vectorshift.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# LLM & AI nodes

> Language models, vision, audio, and AI transforms.

Add these nodes with the pipeline builder: `pipeline.add(name="...").<node>(...)`. Each entry lists the node's configuration parameters. See the [Pipeline reference](/sdk/pipeline/reference) for `add`, `run`, and lifecycle methods.

## `ai_audio_operations`

Leverage AI for Audio operations

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").ai_audio_operations()
  ```
</CodeGroup>

**Parameters**

<ParamField path="sub_type" type="str" default="''" />

## `ai_fill_pdf`

Fill out a PDF with form fields using AI. The AI will understand and fill each field using provided context. To convert your PDF to have fillable input fields, use: [https://www.sejda.com/pdf-forms](https://www.sejda.com/pdf-forms)

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").ai_fill_pdf(provider="anthropic", context="...", file=...)
  ```
</CodeGroup>

**Parameters**

<ParamField path="select_pages" type="bool" default="False">
  Whether to select specific pages to fill
</ParamField>

<ParamField path="provider" type="str" required>
  The model provider

  <Expandable title="Allowed values">
    `anthropic`, `azure`, `bedrock`, `cohere`, `custom`, `fireworks`, `google`, `groq`, `openai`, `perplexity`, `together`, `xai`
  </Expandable>
</ParamField>

<ParamField path="model" type="str" default="''">
  The specific model for filling the PDF

  <Expandable title="Allowed values">
    `MiniMaxAI/MiniMax-M2.5`, `MiniMaxAI/MiniMax-M2.7`, `Qwen/QwQ-32B-Preview`, `Qwen/Qwen2.5-72B-Instruct-Turbo-lora`, `Qwen/Qwen2.5-7B-Instruct-Turbo`, `Qwen/Qwen3-235B-A22B-Instruct-2507-tput`, `Qwen/Qwen3-235B-A22B-fp8-tput`, `Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8`, `Qwen/Qwen3-VL-8B-Instruct`, `Qwen/Qwen3.5-397B-A17B`, `Qwen/Qwen3.5-9B`, `Qwen/Qwen3.6-Plus`, `accounts/fireworks/models/deepseek-v4-pro`, `accounts/fireworks/models/glm-5p1`, `accounts/fireworks/models/gpt-oss-120b`, `accounts/fireworks/models/kimi-k2p5`, `accounts/fireworks/models/kimi-k2p6`, `accounts/fireworks/models/minimax-m2p7`, `accounts/fireworks/models/qwen3-235b-a22b`, `accounts/fireworks/models/qwen3p5-397b-a17b`, `accounts/fireworks/models/qwen3p6-plus`, `amazon.nova-lite-v1:0`, `amazon.nova-micro-v1:0`, `amazon.nova-pro-v1:0`, `amazon.titan-text-express-v1`, `amazon.titan-text-lite-v1`, `chatgpt-4o-latest`, `claude-3-5-haiku-20241022`, `claude-3-7-sonnet-20250219`, `claude-3-haiku-20240307`, `claude-haiku-4-5-20251001`, `claude-opus-4-1-20250805`, `claude-opus-4-20250514`, `claude-opus-4-5-20251101`, `claude-opus-4-6`, `claude-opus-4-7`, `claude-opus-4-8`, `claude-sonnet-4-20250514`, `claude-sonnet-4-5`, `claude-sonnet-4-6`, `command-nightly`, `command-r-08-2024`, `command-r-plus-08-2024`, `deepcogito/cogito-v2-1-671b`, `deepseek-ai/DeepSeek-R1-Distill-Llama-70B`, `deepseek-ai/DeepSeek-V3`, `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/deepseek-llm-67b-chat`, `gemini-2.0-flash-001`, `gemini-2.0-flash-lite-preview-02-05`, `gemini-2.5-flash`, `gemini-2.5-pro`, `gemini-3-flash-preview`, `gemini-3-pro-preview`, `gemini-3.1-flash-lite-preview`, `gemini-3.1-pro-preview`, `gemini-3.5-flash`, `gemma2-9b-it`, `google/gemma-2-27b-it`, `google/gemma-2-9b-it`, `google/gemma-2b-it`, `google/gemma-3n-E4B-it`, `google/gemma-4-31B-it`, `gpt-3.5-turbo`, `gpt-4`, `gpt-4-turbo`, `gpt-4-turbo-2024-04-09`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `gpt-4o`, `gpt-4o-2024-08-06`, `gpt-4o-mini`, `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `gpt-5.1`, `gpt-5.1-codex`, `gpt-5.1-codex-mini`, `gpt-5.2`, `gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.5`, `grok-2`, `grok-2-vision`, `grok-3-beta`, `grok-3-fast-beta`, `grok-3-mini-beta`, `grok-3-mini-fast-beta`, `grok-4`, `grok-4-0629`, `grok-4-0709`, `grok-4-fast-non-reasoning`, `grok-4-fast-reasoning`, `grok-4-latest`, `llama-3.1-8b-instant`, `llama-3.3-70b-versatile`, `meta-llama/Llama-3-70b-chat-hf`, `meta-llama/Llama-3-8b-chat-hf`, `meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo`, `meta-llama/Llama-3.2-3B-Instruct-Turbo`, `meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo`, `meta-llama/Llama-3.3-70B-Instruct-Turbo`, `meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8`, `meta-llama/Llama-4-Scout-17B-16E-Instruct`, `meta-llama/Meta-Llama-3-70B-Instruct-Lite`, `meta-llama/Meta-Llama-3-70B-Instruct-Turbo`, `meta-llama/Meta-Llama-3-8B-Instruct-Lite`, `meta-llama/Meta-Llama-3-8B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo`, `meta.llama3-8b-instruct-v1:0`, `mistralai/Mistral-7B-Instruct-v0.1`, `mistralai/Mistral-7B-Instruct-v0.2`, `mistralai/Mistral-7B-Instruct-v0.3`, `mistralai/Mixtral-8x22B-Instruct-v0.1`, `mistralai/Mixtral-8x7B-Instruct-v0.1`, `mixtral-8x7b-32768`, `moonshotai/Kimi-K2-Instruct`, `moonshotai/Kimi-K2.5`, `moonshotai/Kimi-K2.6`, `o1`, `o3`, `o3-mini`, `o4-mini`, `openai/gpt-oss-120b`, `openai/gpt-oss-20b`, `perplexity-ai/r1-1776`, `r1-1776`, `sonar`, `sonar-deep-research`, `sonar-pro`, `sonar-reasoning-pro`, `us.anthropic.claude-haiku-4-5-20251001-v1:0`, `us.anthropic.claude-opus-4-1-20250805-v1:0`, `us.anthropic.claude-opus-4-5-20251101-v1:0`, `us.anthropic.claude-opus-4-6-v1`, `us.anthropic.claude-sonnet-4-20250514-v1:0`, `us.anthropic.claude-sonnet-4-5-20250929-v1:0`, `us.anthropic.claude-sonnet-4-6`, `us.meta.llama3-1-70b-instruct-v1:0`, `us.meta.llama3-1-8b-instruct-v1:0`, `us.meta.llama3-2-11b-instruct-v1:0`, `us.meta.llama3-2-1b-instruct-v1:0`, `us.meta.llama3-2-3b-instruct-v1:0`, `us.meta.llama3-2-90b-instruct-v1:0`, `zai-org/GLM-4.5-Air-FP8`, `zai-org/GLM-5`, `zai-org/GLM-5.1`
  </Expandable>
</ParamField>

<ParamField path="context" type="str" required>
  Context used by LLM to fill PDF fields
</ParamField>

<ParamField path="file" type="AcceptsFile" required>
  The PDF with form fields to be filled
</ParamField>

<ParamField path="selected_pages" type="str" default="''">
  PDF page range
</ParamField>

## `ai_image_operations`

Leverage AI for Image operations

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").ai_image_operations()
  ```
</CodeGroup>

**Parameters**

<ParamField path="sub_type" type="str" default="''" />

## `ai_image_to_image`

Modify and edit images using AI by providing modification instructions

<Info>Platform docs: [Modify and edit images using AI by providing modification instructions](/nodes/image-to-image/overview)</Info>

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").ai_image_to_image(provider="google", model="gemini-2.5-flash-image", api_key="...", size="1024x1024")
  ```
</CodeGroup>

**Parameters**

<ParamField path="use_personal_api_key" type="bool" default="False">
  Use your personal API key
</ParamField>

<ParamField path="provider" type="str" required>
  Select the model provider.
  One of: `google`, `openai`
</ParamField>

<ParamField path="model" type="str" required>
  Select the image-to-image model

  <Expandable title="Allowed values">
    `gemini-2.5-flash-image`, `gemini-3-pro-image-preview`, `gpt-3.5-turbo`, `gpt-4`, `gpt-4-turbo`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `gpt-image-1.5`, `gpt-image-2`, `o1`, `o3`, `o3-mini`, `o4-mini`
  </Expandable>
</ParamField>

<ParamField path="prompt" type="str" default="''">
  Tell the AI model how you would like it to modify the images. Be as specific as possible. For example, you can instruct the model to change colors, add elements, apply artistic styles, or blend multiple images. Must not be empty.
</ParamField>

<ParamField path="api_key" type="str" required>
  Input your personal API key from the model provider. Note: if you do not have access to the selected model, the workflow will not run
</ParamField>

<ParamField path="aspect_ratio" type="str" default="'1:1'">
  Select the aspect ratio for the output image.

  <Expandable title="Allowed values">
    `16:9`, `1:1`, `21:9`, `2:3`, `3:2`, `3:4`, `4:3`, `4:5`, `5:4`, `9:16`
  </Expandable>
</ParamField>

<ParamField path="images" type="AcceptsImageList">
  Array of input images to modify. Provide 1-3 images for best results.
</ParamField>

<ParamField path="size" type="str" required>
  Select the size.
  One of: `1024x1024`, `1024x1536`, `1024x1792`, `1536x1024`, `1792x1024`, `256x256`, `512x512`, `auto`
</ParamField>

## `ai_image_to_text`

Generate Text from Image using AI

<Info>Platform docs: [Generate Text from Image using AI](/nodes/image-to-text/overview)</Info>

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").ai_image_to_text(provider="anthropic", model="chatgpt-4o-latest", api_key="...", image=...)
  ```
</CodeGroup>

**Parameters**

<ParamField path="use_personal_api_key" type="bool" default="False">
  Use your personal API key
</ParamField>

<ParamField path="json_response" type="bool" default="False">
  Return the response as a JSON object
</ParamField>

<ParamField path="stream" type="bool" default="False">
  Stream the response
</ParamField>

<ParamField path="provider" type="str" required>
  Select the provider that will be used to analyze image.
  One of: `anthropic`, `fireworks`, `google`, `openai`, `together`, `xai`
</ParamField>

<ParamField path="model" type="str" required>
  Select the image analyzing model.

  <Expandable title="Allowed values">
    `chatgpt-4o-latest`, `claude-3-5-haiku-20241022`, `claude-3-7-sonnet-20250219`, `claude-3-haiku-20240307`, `claude-haiku-4-5-20251001`, `claude-opus-4-1-20250805`, `claude-opus-4-20250514`, `claude-opus-4-5-20251101`, `claude-opus-4-6`, `claude-opus-4-7`, `claude-opus-4-8`, `claude-sonnet-4-20250514`, `claude-sonnet-4-5`, `claude-sonnet-4-6`, `gemini-2.0-flash-001`, `gemini-2.0-flash-lite-preview-02-05`, `gemini-2.5-flash`, `gemini-2.5-pro`, `gemini-3-flash-preview`, `gemini-3-pro-preview`, `gemini-3.1-flash-lite-preview`, `gemini-3.1-pro-preview`, `gemini-3.5-flash`, `gpt-3.5-turbo`, `gpt-4`, `gpt-4-turbo`, `gpt-4-turbo-2024-04-09`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `gpt-4o`, `gpt-4o-2024-08-06`, `gpt-4o-mini`, `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `gpt-5.1`, `gpt-5.1-codex`, `gpt-5.1-codex-mini`, `gpt-5.2`, `gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.5`, `grok-2-vision`, `o1`, `o3`, `o3-mini`, `o4-mini`
  </Expandable>
</ParamField>

<ParamField path="prompt" type="str" default="''">
  Instructions on what you want to analyze from the image.
</ParamField>

<ParamField path="system" type="str" default="''">
  Tell the AI model how you would like it to respond. Be as specific as possible. For example, you can instruct the model on what tone to respond in or how to respond given the information you provide
</ParamField>

<ParamField path="api_key" type="str" required>
  Input your personal API key from the model provider. Note: if you do not have access to the selected model, the workflow will not run
</ParamField>

<ParamField path="image" type="AcceptsImage" required>
  The image to analyze. For agent tool calls, pass an existing file reference such as $history.MESSAGE_ID, $tool.CALL\_ID.OUTPUT\_KEY, or \$input.NAME; never pass an empty string.
</ParamField>

<ParamField path="json_schema" type="str" required>
  The JSON schema to use for the response
</ParamField>

<ParamField path="sampling" type="SamplingConfig" />

<ParamField path="max_tokens" type="int">
  The maximum number of tokens to generate
</ParamField>

<ParamField path="temperature" type="float">
  The temperature of the model
</ParamField>

<ParamField path="top_p" type="float">
  The top-p value
</ParamField>

## `ai_operations`

Leverage AI for various tasks

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").ai_operations()
  ```
</CodeGroup>

**Parameters**

<ParamField path="sub_type" type="str" default="''" />

## `ai_routing`

Route the execution flow to different paths based on the value of the conditions.

<Info>Platform docs: [Route the execution flow to different paths based on the value of the conditions.](/nodes/ai-routing/overview)</Info>

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").ai_routing(provider="anthropic", input_query="...")
  ```
</CodeGroup>

**Parameters**

<ParamField path="provider" type="str" required>
  The model provider

  <Expandable title="Allowed values">
    `anthropic`, `azure`, `bedrock`, `cohere`, `custom`, `fireworks`, `google`, `groq`, `openai`, `perplexity`, `together`, `xai`
  </Expandable>
</ParamField>

<ParamField path="enable_shared_memory" type="bool" default="False">
  If enabled, Shared Memory will be included as context for routing decisions
</ParamField>

<ParamField path="model" type="str" default="''">
  The specific model for categorization

  <Expandable title="Allowed values">
    `MiniMaxAI/MiniMax-M2.5`, `MiniMaxAI/MiniMax-M2.7`, `Qwen/QwQ-32B-Preview`, `Qwen/Qwen2.5-72B-Instruct-Turbo-lora`, `Qwen/Qwen2.5-7B-Instruct-Turbo`, `Qwen/Qwen3-235B-A22B-Instruct-2507-tput`, `Qwen/Qwen3-235B-A22B-fp8-tput`, `Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8`, `Qwen/Qwen3-VL-8B-Instruct`, `Qwen/Qwen3.5-397B-A17B`, `Qwen/Qwen3.5-9B`, `Qwen/Qwen3.6-Plus`, `accounts/fireworks/models/deepseek-v4-pro`, `accounts/fireworks/models/glm-5p1`, `accounts/fireworks/models/gpt-oss-120b`, `accounts/fireworks/models/kimi-k2p5`, `accounts/fireworks/models/kimi-k2p6`, `accounts/fireworks/models/minimax-m2p7`, `accounts/fireworks/models/qwen3-235b-a22b`, `accounts/fireworks/models/qwen3p5-397b-a17b`, `accounts/fireworks/models/qwen3p6-plus`, `amazon.nova-lite-v1:0`, `amazon.nova-micro-v1:0`, `amazon.nova-pro-v1:0`, `amazon.titan-text-express-v1`, `amazon.titan-text-lite-v1`, `chatgpt-4o-latest`, `claude-3-5-haiku-20241022`, `claude-3-7-sonnet-20250219`, `claude-3-haiku-20240307`, `claude-haiku-4-5-20251001`, `claude-opus-4-1-20250805`, `claude-opus-4-20250514`, `claude-opus-4-5-20251101`, `claude-opus-4-6`, `claude-opus-4-7`, `claude-opus-4-8`, `claude-sonnet-4-20250514`, `claude-sonnet-4-5`, `claude-sonnet-4-6`, `command-nightly`, `command-r-08-2024`, `command-r-plus-08-2024`, `deepcogito/cogito-v2-1-671b`, `deepseek-ai/DeepSeek-R1-Distill-Llama-70B`, `deepseek-ai/DeepSeek-V3`, `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/deepseek-llm-67b-chat`, `gemini-2.0-flash-001`, `gemini-2.0-flash-lite-preview-02-05`, `gemini-2.5-flash`, `gemini-2.5-pro`, `gemini-3-flash-preview`, `gemini-3-pro-preview`, `gemini-3.1-flash-lite-preview`, `gemini-3.1-pro-preview`, `gemini-3.5-flash`, `gemma2-9b-it`, `google/gemma-2-27b-it`, `google/gemma-2-9b-it`, `google/gemma-2b-it`, `google/gemma-3n-E4B-it`, `google/gemma-4-31B-it`, `gpt-3.5-turbo`, `gpt-4`, `gpt-4-turbo`, `gpt-4-turbo-2024-04-09`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `gpt-4o`, `gpt-4o-2024-08-06`, `gpt-4o-mini`, `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `gpt-5.1`, `gpt-5.1-codex`, `gpt-5.1-codex-mini`, `gpt-5.2`, `gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.5`, `grok-2`, `grok-2-vision`, `grok-3-beta`, `grok-3-fast-beta`, `grok-3-mini-beta`, `grok-3-mini-fast-beta`, `grok-4`, `grok-4-0629`, `grok-4-0709`, `grok-4-fast-non-reasoning`, `grok-4-fast-reasoning`, `grok-4-latest`, `llama-3.1-8b-instant`, `llama-3.3-70b-versatile`, `meta-llama/Llama-3-70b-chat-hf`, `meta-llama/Llama-3-8b-chat-hf`, `meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo`, `meta-llama/Llama-3.2-3B-Instruct-Turbo`, `meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo`, `meta-llama/Llama-3.3-70B-Instruct-Turbo`, `meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8`, `meta-llama/Llama-4-Scout-17B-16E-Instruct`, `meta-llama/Meta-Llama-3-70B-Instruct-Lite`, `meta-llama/Meta-Llama-3-70B-Instruct-Turbo`, `meta-llama/Meta-Llama-3-8B-Instruct-Lite`, `meta-llama/Meta-Llama-3-8B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo`, `meta.llama3-8b-instruct-v1:0`, `mistralai/Mistral-7B-Instruct-v0.1`, `mistralai/Mistral-7B-Instruct-v0.2`, `mistralai/Mistral-7B-Instruct-v0.3`, `mistralai/Mixtral-8x22B-Instruct-v0.1`, `mistralai/Mixtral-8x7B-Instruct-v0.1`, `mixtral-8x7b-32768`, `moonshotai/Kimi-K2-Instruct`, `moonshotai/Kimi-K2.5`, `moonshotai/Kimi-K2.6`, `o1`, `o3`, `o3-mini`, `o4-mini`, `openai/gpt-oss-120b`, `openai/gpt-oss-20b`, `perplexity-ai/r1-1776`, `r1-1776`, `sonar`, `sonar-deep-research`, `sonar-pro`, `sonar-reasoning-pro`, `us.anthropic.claude-haiku-4-5-20251001-v1:0`, `us.anthropic.claude-opus-4-1-20250805-v1:0`, `us.anthropic.claude-opus-4-5-20251101-v1:0`, `us.anthropic.claude-opus-4-6-v1`, `us.anthropic.claude-sonnet-4-20250514-v1:0`, `us.anthropic.claude-sonnet-4-5-20250929-v1:0`, `us.anthropic.claude-sonnet-4-6`, `us.meta.llama3-1-70b-instruct-v1:0`, `us.meta.llama3-1-8b-instruct-v1:0`, `us.meta.llama3-2-11b-instruct-v1:0`, `us.meta.llama3-2-1b-instruct-v1:0`, `us.meta.llama3-2-3b-instruct-v1:0`, `us.meta.llama3-2-90b-instruct-v1:0`, `zai-org/GLM-4.5-Air-FP8`, `zai-org/GLM-5`, `zai-org/GLM-5.1`
  </Expandable>
</ParamField>

<ParamField path="conditions" type="list[str]" default="[]" />

<ParamField path="input_query" type="str" required>
  Specify the message that the AI router will classify
</ParamField>

<ParamField path="outputs" type="dict" default="{}" />

<ParamField path="shared_memory" type="str" default="''">
  The shared memory that will be used as context for AI to determine the routing
</ParamField>

<ParamField path="sampling" type="SamplingConfig" />

<ParamField path="max_tokens" type="int">
  The maximum number of tokens to generate
</ParamField>

<ParamField path="temperature" type="float">
  The temperature of the model
</ParamField>

<ParamField path="top_p" type="float">
  The top-p value
</ParamField>

## `ai_speech_to_text`

Generate Text from Audio using AI

<Info>Platform docs: [Generate Text from Audio using AI](/nodes/speech-to-text/overview)</Info>

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").ai_speech_to_text(provider="deepgram", model="base", api_key="...", audio=...)
  ```
</CodeGroup>

**Parameters**

<ParamField path="use_personal_api_key" type="bool" default="False">
  Use your personal API key
</ParamField>

<ParamField path="provider" type="str" required>
  Select the model provider.
  One of: `deepgram`, `google`, `openai`
</ParamField>

<ParamField path="model" type="str" required>
  Select the speech-to-text model

  <Expandable title="Allowed values">
    `base`, `enhanced`, `gemini-2.0-flash-001`, `gemini-2.5-flash`, `gemini-2.5-pro`, `gemini-3-flash-preview`, `gemini-3-pro-preview`, `gemini-3.1-flash-lite-preview`, `gemini-3.1-pro-preview`, `gemini-3.5-flash`, `gpt-3.5-turbo`, `gpt-4`, `gpt-4-turbo`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `nova`, `nova-2`, `nova-3`, `o1`, `o3`, `o3-mini`, `o4-mini`, `whisper-1`
  </Expandable>
</ParamField>

<ParamField path="api_key" type="str" required>
  Input your personal API key from the model provider. Note: if you do not have access to the selected model, the workflow will not run
</ParamField>

<ParamField path="audio" type="AcceptsAudio" required>
  The audio for conversion
</ParamField>

<ParamField path="tier" type="str" required>
  Select the tier

  <Expandable title="Allowed values">
    `atc`, `automotive`, `conversationalai`, `drivethru`, `finance`, `general`, `medical`, `meeting`, `phonecall`, `video`, `voicemail`
  </Expandable>
</ParamField>

## `ai_text_to_image`

Generate Image from Text using AI

<Info>Platform docs: [Generate Image from Text using AI](/nodes/text-to-image/overview)</Info>

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").ai_text_to_image(provider="flux", model="Stable Diffusion 1.6", api_key="...", aspect_ratio="16:9")
  ```
</CodeGroup>

**Parameters**

<ParamField path="use_personal_api_key" type="bool" default="False">
  Use your personal API key
</ParamField>

<ParamField path="provider" type="str" required>
  Select the model provider.
  One of: `flux`, `google`, `openai`, `stabilityai`, `xai`
</ParamField>

<ParamField path="model" type="str" required>
  Select the text-to-image model

  <Expandable title="Allowed values">
    `Stable Diffusion 1.6`, `Stable Diffusion 3 Large`, `Stable Diffusion 3 Large Turbo`, `Stable Diffusion 3 Medium`, `Stable Diffusion Core`, `Stable Diffusion Ultra`, `Stable Diffusion XL`, `dall-e-2`, `dall-e-3`, `flux-dev`, `flux-pro`, `flux-schnell`, `gemini-2.5-flash-image`, `gemini-3-pro-image-preview`, `gpt-3.5-turbo`, `gpt-4`, `gpt-4-turbo`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `gpt-image-1.5`, `gpt-image-2`, `grok-2-image`, `o1`, `o3`, `o3-mini`, `o4-mini`
  </Expandable>
</ParamField>

<ParamField path="prompt" type="str" default="''">
  Tell the AI model how you would like it to respond. Be as specific as possible. For example, you can instruct the model to use bright colors. Must not be empty.
</ParamField>

<ParamField path="api_key" type="str" required>
  Input your personal API key from the model provider. Note: if you do not have access to the selected model, the workflow will not run
</ParamField>

<ParamField path="aspect_ratio" type="str" required>
  Select the aspect ratio.

  <Expandable title="Allowed values">
    `16:9`, `1:1`, `21:9`, `2:3`, `3:2`, `3:4`, `4:3`, `4:5`, `5:4`, `9:16`, `9:21`
  </Expandable>
</ParamField>

<ParamField path="size" type="str" required>
  Select the size.
  One of: `1024x1024`, `1024x1536`, `1024x1792`, `1536x1024`, `1792x1024`, `256x256`, `512x512`, `auto`
</ParamField>

## `ai_text_to_speech`

Generate Audio from text using AI

<Info>Platform docs: [Generate Audio from text using AI](/nodes/text-to-speech/overview)</Info>

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").ai_text_to_speech(text="...", api_key="...")
  ```
</CodeGroup>

**Parameters**

<ParamField path="use_personal_api_key" type="bool" default="False">
  Use your personal API key
</ParamField>

<ParamField path="provider" type="str" default="'openai'">
  Select the model provider.
  One of: `eleven_labs`, `openai`
</ParamField>

<ParamField path="model" type="str" default="'tts-1-hd'">
  Select the text-to-speech model

  <Expandable title="Allowed values">
    `eleven_flash_v2`, `eleven_flash_v2_5`, `eleven_monolingual_v1`, `eleven_multilingual_v1`, `eleven_multilingual_v2`, `eleven_turbo_v2`, `eleven_turbo_v2_5`, `gpt-3.5-turbo`, `gpt-4`, `gpt-4-turbo`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `o1`, `o3`, `o3-mini`, `o4-mini`, `tts-1`, `tts-1-hd`
  </Expandable>
</ParamField>

<ParamField path="text" type="str" required>
  The string input for conversion.
</ParamField>

<ParamField path="api_key" type="str" required>
  Input your personal API key from the model provider. Note: if you do not have access to the selected model, the workflow will not run
</ParamField>

<ParamField path="voice" type="str" default="'alloy'">
  Select the voice

  <Expandable title="Allowed values">
    `Alice`, `Aria`, `Bill`, `Brian`, `Callum`, `Charlie`, `Charlotte`, `Chris`, `Daniel`, `Eric`, `George`, `Jessica`, `Laura`, `Liam`, `Lily`, `Matilda`, `River`, `Roger`, `Sarah`, `Will`, `alloy`, `echo`, `fable`, `nova`, `onyx`, `shimmer`
  </Expandable>
</ParamField>

## `categorizer`

Categorize text using AI into custom-defined buckets

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").categorizer(provider="anthropic", text="...")
  ```
</CodeGroup>

**Parameters**

<ParamField path="justification" type="bool" default="False">
  Include the AI's justification for its score
</ParamField>

<ParamField path="provider" type="str" required>
  The model provider

  <Expandable title="Allowed values">
    `anthropic`, `aws`, `azure`, `bedrock`, `cohere`, `custom`, `fireworks`, `google`, `groq`, `openai`, `perplexity`, `together`, `xai`
  </Expandable>
</ParamField>

<ParamField path="model" type="str" default="''">
  The specific model for categorization

  <Expandable title="Allowed values">
    `MiniMaxAI/MiniMax-M2.5`, `MiniMaxAI/MiniMax-M2.7`, `Qwen/QwQ-32B-Preview`, `Qwen/Qwen2.5-72B-Instruct-Turbo-lora`, `Qwen/Qwen2.5-7B-Instruct-Turbo`, `Qwen/Qwen3-235B-A22B-Instruct-2507-tput`, `Qwen/Qwen3-235B-A22B-fp8-tput`, `Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8`, `Qwen/Qwen3-VL-8B-Instruct`, `Qwen/Qwen3.5-397B-A17B`, `Qwen/Qwen3.5-9B`, `Qwen/Qwen3.6-Plus`, `accounts/fireworks/models/deepseek-v4-pro`, `accounts/fireworks/models/glm-5p1`, `accounts/fireworks/models/gpt-oss-120b`, `accounts/fireworks/models/kimi-k2p5`, `accounts/fireworks/models/kimi-k2p6`, `accounts/fireworks/models/minimax-m2p7`, `accounts/fireworks/models/qwen3-235b-a22b`, `accounts/fireworks/models/qwen3p5-397b-a17b`, `accounts/fireworks/models/qwen3p6-plus`, `amazon.nova-lite-v1:0`, `amazon.nova-micro-v1:0`, `amazon.nova-pro-v1:0`, `amazon.titan-text-express-v1`, `amazon.titan-text-lite-v1`, `chatgpt-4o-latest`, `claude-3-5-haiku-20241022`, `claude-3-7-sonnet-20250219`, `claude-3-haiku-20240307`, `claude-haiku-4-5-20251001`, `claude-opus-4-1-20250805`, `claude-opus-4-20250514`, `claude-opus-4-5-20251101`, `claude-opus-4-6`, `claude-opus-4-7`, `claude-opus-4-8`, `claude-sonnet-4-20250514`, `claude-sonnet-4-5`, `claude-sonnet-4-6`, `command-nightly`, `command-r-08-2024`, `command-r-plus-08-2024`, `deepcogito/cogito-v2-1-671b`, `deepseek-ai/DeepSeek-R1-Distill-Llama-70B`, `deepseek-ai/DeepSeek-V3`, `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/deepseek-llm-67b-chat`, `gemini-2.0-flash-001`, `gemini-2.0-flash-lite-preview-02-05`, `gemini-2.5-flash`, `gemini-2.5-pro`, `gemini-3-flash-preview`, `gemini-3-pro-preview`, `gemini-3.1-flash-lite-preview`, `gemini-3.1-pro-preview`, `gemini-3.5-flash`, `gemma2-9b-it`, `google/gemma-2-27b-it`, `google/gemma-2-9b-it`, `google/gemma-2b-it`, `google/gemma-3n-E4B-it`, `google/gemma-4-31B-it`, `gpt-3.5-turbo`, `gpt-4`, `gpt-4-turbo`, `gpt-4-turbo-2024-04-09`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `gpt-4o`, `gpt-4o-2024-08-06`, `gpt-4o-mini`, `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `gpt-5.1`, `gpt-5.1-codex`, `gpt-5.1-codex-mini`, `gpt-5.2`, `gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.5`, `grok-2`, `grok-2-vision`, `grok-3-beta`, `grok-3-fast-beta`, `grok-3-mini-beta`, `grok-3-mini-fast-beta`, `grok-4`, `grok-4-0629`, `grok-4-0709`, `grok-4-fast-non-reasoning`, `grok-4-fast-reasoning`, `grok-4-latest`, `llama-3.1-8b-instant`, `llama-3.3-70b-versatile`, `meta-llama/Llama-3-70b-chat-hf`, `meta-llama/Llama-3-8b-chat-hf`, `meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo`, `meta-llama/Llama-3.2-3B-Instruct-Turbo`, `meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo`, `meta-llama/Llama-3.3-70B-Instruct-Turbo`, `meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8`, `meta-llama/Llama-4-Scout-17B-16E-Instruct`, `meta-llama/Meta-Llama-3-70B-Instruct-Lite`, `meta-llama/Meta-Llama-3-70B-Instruct-Turbo`, `meta-llama/Meta-Llama-3-8B-Instruct-Lite`, `meta-llama/Meta-Llama-3-8B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo`, `meta.llama3-8b-instruct-v1:0`, `mistralai/Mistral-7B-Instruct-v0.1`, `mistralai/Mistral-7B-Instruct-v0.2`, `mistralai/Mistral-7B-Instruct-v0.3`, `mistralai/Mixtral-8x22B-Instruct-v0.1`, `mistralai/Mixtral-8x7B-Instruct-v0.1`, `mixtral-8x7b-32768`, `moonshotai/Kimi-K2-Instruct`, `moonshotai/Kimi-K2.5`, `moonshotai/Kimi-K2.6`, `o1`, `o3`, `o3-mini`, `o4-mini`, `openai/gpt-oss-120b`, `openai/gpt-oss-20b`, `perplexity-ai/r1-1776`, `r1-1776`, `sonar`, `sonar-deep-research`, `sonar-pro`, `sonar-reasoning-pro`, `us.anthropic.claude-haiku-4-5-20251001-v1:0`, `us.anthropic.claude-opus-4-1-20250805-v1:0`, `us.anthropic.claude-opus-4-5-20251101-v1:0`, `us.anthropic.claude-opus-4-6-v1`, `us.anthropic.claude-sonnet-4-20250514-v1:0`, `us.anthropic.claude-sonnet-4-5-20250929-v1:0`, `us.anthropic.claude-sonnet-4-6`, `us.meta.llama3-1-70b-instruct-v1:0`, `us.meta.llama3-1-8b-instruct-v1:0`, `us.meta.llama3-2-11b-instruct-v1:0`, `us.meta.llama3-2-1b-instruct-v1:0`, `us.meta.llama3-2-3b-instruct-v1:0`, `us.meta.llama3-2-90b-instruct-v1:0`, `zai-org/GLM-4.5-Air-FP8`, `zai-org/GLM-5`, `zai-org/GLM-5.1`
  </Expandable>
</ParamField>

<ParamField path="text" type="str" required>
  The text that will be categorized
</ParamField>

<ParamField path="additional_context" type="str" default="''">
  Provide any additional context or instructions
</ParamField>

<ParamField path="fields" type="ListType | list[List[Dict[str, Any]]] | list[NameDescription]" default="[]">
  The fields to be categorized
</ParamField>

<ParamField path="sampling" type="SamplingConfig" />

<ParamField path="max_tokens" type="int">
  The maximum number of tokens to generate
</ParamField>

<ParamField path="temperature" type="float">
  The temperature of the model
</ParamField>

<ParamField path="top_p" type="float">
  The top-p value
</ParamField>

## `email_validator`

Validate an email address

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").email_validator(api_key="...", email_to_validate="...")
  ```
</CodeGroup>

**Parameters**

<ParamField path="model" type="str" default="'regex'">
  The validation model to use
  One of: `custom-validator`, `regex`
</ParamField>

<ParamField path="api_key" type="str" required>
  The API key to use
</ParamField>

<ParamField path="email_to_validate" type="str" required>
  The email you want to validate
</ParamField>

<ParamField path="provider" type="str" default="'hunter'">
  The validation provider to use
  One of: `debounce`, `hunter`
</ParamField>

## `extract_data`

Extract key pieces of information or a list of information from a input text.

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").extract_data(text="...", fields=..., processed_outputs=...)
  ```
</CodeGroup>

**Parameters**

<ParamField path="model" type="str" default="'gpt-4o'" />

<ParamField path="text" type="str" required />

<ParamField path="additional_context" type="str" default="''" />

<ParamField path="fields" type="ListType | list[List[Dict[str, Any]]] | list[NameTypeDescription]" required />

<ParamField path="processed_outputs" type="dict" required />

<ParamField path="provider" type="str" default="'openai'" />

## `image_gen`

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").image_gen()
  ```
</CodeGroup>

**Parameters**

<ParamField path="model" type="str" default="'gpt-4-1106-preview'" />

<ParamField path="prompt" type="str" default="''" />

<ParamField path="aspect_ratio" type="str" default="'1:1'" />

<ParamField path="image_count" type="str" default="'1'" />

<ParamField path="provider" type="str" default="'llmOpenAI'" />

<ParamField path="size" type="str" default="'512x512'" />

## `llm`

LLM

<Info>Platform docs: [LLM](/platform/pipelines/llms/llm-node)</Info>

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").llm(provider="anthropic", api_key="...", json_schema="...")
  ```
</CodeGroup>

**Parameters**

<ParamField path="provider" type="str" required>
  Select the LLM provider to be used

  <Expandable title="Allowed values">
    `anthropic`, `azure`, `bedrock`, `cohere`, `custom`, `fireworks`, `google`, `groq`, `openai`, `perplexity`, `together`, `xai`
  </Expandable>
</ParamField>

<ParamField path="stream" type="bool" default="False">
  Whether to stream the response
</ParamField>

<ParamField path="use_personal_api_key" type="bool" default="True" />

<ParamField path="json_response" type="bool" default="False">
  Whether to return the response as a JSON object
</ParamField>

<ParamField path="show_sources" type="bool" default="True">
  Whether to show the sources used to generate the response
</ParamField>

<ParamField path="model" type="str" default="''">
  Select the LLM model to be used

  <Expandable title="Allowed values">
    `MiniMaxAI/MiniMax-M2.5`, `MiniMaxAI/MiniMax-M2.7`, `Qwen/QwQ-32B-Preview`, `Qwen/Qwen2.5-72B-Instruct-Turbo-lora`, `Qwen/Qwen2.5-7B-Instruct-Turbo`, `Qwen/Qwen3-235B-A22B-Instruct-2507-tput`, `Qwen/Qwen3-235B-A22B-fp8-tput`, `Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8`, `Qwen/Qwen3-VL-8B-Instruct`, `Qwen/Qwen3.5-397B-A17B`, `Qwen/Qwen3.5-9B`, `Qwen/Qwen3.6-Plus`, `accounts/fireworks/models/deepseek-v4-pro`, `accounts/fireworks/models/glm-5p1`, `accounts/fireworks/models/gpt-oss-120b`, `accounts/fireworks/models/kimi-k2p5`, `accounts/fireworks/models/kimi-k2p6`, `accounts/fireworks/models/minimax-m2p7`, `accounts/fireworks/models/qwen3-235b-a22b`, `accounts/fireworks/models/qwen3p5-397b-a17b`, `accounts/fireworks/models/qwen3p6-plus`, `amazon.nova-lite-v1:0`, `amazon.nova-micro-v1:0`, `amazon.nova-pro-v1:0`, `amazon.titan-text-express-v1`, `amazon.titan-text-lite-v1`, `chatgpt-4o-latest`, `claude-3-5-haiku-20241022`, `claude-3-7-sonnet-20250219`, `claude-3-haiku-20240307`, `claude-haiku-4-5-20251001`, `claude-opus-4-1-20250805`, `claude-opus-4-20250514`, `claude-opus-4-5-20251101`, `claude-opus-4-6`, `claude-opus-4-7`, `claude-opus-4-8`, `claude-sonnet-4-20250514`, `claude-sonnet-4-5`, `claude-sonnet-4-6`, `command-nightly`, `command-r-08-2024`, `command-r-plus-08-2024`, `deepcogito/cogito-v2-1-671b`, `deepseek-ai/DeepSeek-R1-Distill-Llama-70B`, `deepseek-ai/DeepSeek-V3`, `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/deepseek-llm-67b-chat`, `gemini-2.0-flash-001`, `gemini-2.0-flash-lite-preview-02-05`, `gemini-2.5-flash`, `gemini-2.5-pro`, `gemini-3-flash-preview`, `gemini-3-pro-preview`, `gemini-3.1-flash-lite-preview`, `gemini-3.1-pro-preview`, `gemini-3.5-flash`, `gemma2-9b-it`, `google/gemma-2-27b-it`, `google/gemma-2-9b-it`, `google/gemma-2b-it`, `google/gemma-3n-E4B-it`, `google/gemma-4-31B-it`, `gpt-3.5-turbo`, `gpt-4`, `gpt-4-turbo`, `gpt-4-turbo-2024-04-09`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `gpt-4o`, `gpt-4o-2024-08-06`, `gpt-4o-mini`, `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `gpt-5.1`, `gpt-5.1-codex`, `gpt-5.1-codex-mini`, `gpt-5.2`, `gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.5`, `grok-2`, `grok-2-vision`, `grok-3-beta`, `grok-3-fast-beta`, `grok-3-mini-beta`, `grok-3-mini-fast-beta`, `grok-4`, `grok-4-0629`, `grok-4-0709`, `grok-4-fast-non-reasoning`, `grok-4-fast-reasoning`, `grok-4-latest`, `llama-3.1-8b-instant`, `llama-3.3-70b-versatile`, `meta-llama/Llama-3-70b-chat-hf`, `meta-llama/Llama-3-8b-chat-hf`, `meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo`, `meta-llama/Llama-3.2-3B-Instruct-Turbo`, `meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo`, `meta-llama/Llama-3.3-70B-Instruct-Turbo`, `meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8`, `meta-llama/Llama-4-Scout-17B-16E-Instruct`, `meta-llama/Meta-Llama-3-70B-Instruct-Lite`, `meta-llama/Meta-Llama-3-70B-Instruct-Turbo`, `meta-llama/Meta-Llama-3-8B-Instruct-Lite`, `meta-llama/Meta-Llama-3-8B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo`, `meta.llama3-8b-instruct-v1:0`, `mistralai/Mistral-7B-Instruct-v0.1`, `mistralai/Mistral-7B-Instruct-v0.2`, `mistralai/Mistral-7B-Instruct-v0.3`, `mistralai/Mixtral-8x22B-Instruct-v0.1`, `mistralai/Mixtral-8x7B-Instruct-v0.1`, `mixtral-8x7b-32768`, `moonshotai/Kimi-K2-Instruct`, `moonshotai/Kimi-K2.5`, `moonshotai/Kimi-K2.6`, `o1`, `o3`, `o3-mini`, `o4-mini`, `openai/gpt-oss-120b`, `openai/gpt-oss-20b`, `perplexity-ai/r1-1776`, `r1-1776`, `sonar`, `sonar-deep-research`, `sonar-pro`, `sonar-reasoning-pro`, `us.anthropic.claude-haiku-4-5-20251001-v1:0`, `us.anthropic.claude-opus-4-1-20250805-v1:0`, `us.anthropic.claude-opus-4-5-20251101-v1:0`, `us.anthropic.claude-opus-4-6-v1`, `us.anthropic.claude-sonnet-4-20250514-v1:0`, `us.anthropic.claude-sonnet-4-5-20250929-v1:0`, `us.anthropic.claude-sonnet-4-6`, `us.meta.llama3-1-70b-instruct-v1:0`, `us.meta.llama3-1-8b-instruct-v1:0`, `us.meta.llama3-2-11b-instruct-v1:0`, `us.meta.llama3-2-1b-instruct-v1:0`, `us.meta.llama3-2-3b-instruct-v1:0`, `us.meta.llama3-2-90b-instruct-v1:0`, `zai-org/GLM-4.5-Air-FP8`, `zai-org/GLM-5`, `zai-org/GLM-5.1`
  </Expandable>
</ParamField>

<ParamField path="prompt" type="str" default="''">
  The data that is sent to the LLM. Add data from other nodes with double curly braces e.g., \{\{input\_0.text}}
</ParamField>

<ParamField path="system" type="str" default="''">
  The system prompt to be used
</ParamField>

<ParamField path="api_key" type="str" required>
  Your API key
</ParamField>

<ParamField path="baseUrl" type="str" default="''" />

<ParamField path="citation_metadata" type="list[str]" default="[]">
  The metadata of the sources used to generate the response
</ParamField>

<ParamField path="enable_web_search" type="bool" default="False">
  Enable Claude's built-in web search tool to search the web during response generation
</ParamField>

<ParamField path="jsonSchema" type="str" default="''" />

<ParamField path="json_schema" type="str" required>
  The schema of the JSON response
</ParamField>

<ParamField path="reasoning_effort" type="str" default="'default'">
  Controls the depth of reasoning for GPT-5 models ("none" is only supported on GPT-5.1 variants).
  One of: `default`, `high`, `low`, `medium`, `minimal`, `none`
</ParamField>

<ParamField path="safe_context_token_window" type="bool" default="False">
  If enabled, the context window will be reduced to fit the model's maximum context window.
</ParamField>

<ParamField path="verbosity" type="str" default="'default'">
  Controls the verbosity of GPT-5 responses.
  One of: `default`, `high`, `low`, `medium`
</ParamField>

<ParamField path="sampling" type="SamplingConfig" />

<ParamField path="safety" type="SafetyConfig" />

<ParamField path="retry" type="RetryConfig" />

<ParamField path="enable_moderation" type="bool">
  Whether to enable moderation
</ParamField>

<ParamField path="enable_pii_address" type="bool">
  Whether to enable PII address
</ParamField>

<ParamField path="enable_pii_cc" type="bool">
  Whether to enable PII cc
</ParamField>

<ParamField path="enable_pii_email" type="bool">
  Whether to enable PII email
</ParamField>

<ParamField path="enable_pii_name" type="bool">
  Whether to enable PII name
</ParamField>

<ParamField path="enable_pii_phone" type="bool">
  Whether to enable PII phone
</ParamField>

<ParamField path="enable_pii_ssn" type="bool">
  Whether to enable PII ssn
</ParamField>

<ParamField path="max_retries" type="int">
  The maximum number of retries
</ParamField>

<ParamField path="max_tokens" type="int">
  The maximum amount of input + output tokens the model will take in and generate per run (1 token = 4 characters). Note: different models have different token limits and the workflow will error if the max token is reached.
</ParamField>

<ParamField path="retry_interval_ms" type="int">
  The interval between retries in milliseconds
</ParamField>

<ParamField path="retry_on_failure" type="bool">
  Enable retrying when the node execution fails
</ParamField>

<ParamField path="temperature" type="float">
  The "creativity" of the response - increase the temperature for more creative responses.
</ParamField>

<ParamField path="top_p" type="float">
  The "randomness" of the output - higher Top P values increase the randomness
</ParamField>

<ParamField path="deployment_id" type="str" default="''">
  The deployment ID for the Azure OpenAI model. This is required when using Azure OpenAI services.
</ParamField>

<ParamField path="endpoint" type="str" default="''">
  The Azure OpenAI endpoint URL (e.g., [https://your-resource-name.openai.azure.com](https://your-resource-name.openai.azure.com))
</ParamField>

<ParamField path="thinking_token_limit" type="int" default="24576">
  The maximum number of tokens the model can use for thinking
</ParamField>

<ParamField path="finetuned_model" type="str" default="''">
  Use your finetuned model for response generation. Make sure to select the matching base model from the dropdown.
</ParamField>

<ParamField path="use_finetuned_model" type="bool" default="False" />

<ParamField path="base_url" type="str" default="''">
  The base URL of the custom LLM provider
</ParamField>

<ParamField path="aws_access_key_id" type="str" default="''">
  Your AWS Access Key ID
</ParamField>

<ParamField path="aws_region" type="str" default="'us-east-1'">
  AWS region where Bedrock models are enabled

  <Expandable title="Allowed values">
    `ap-northeast-1`, `ap-south-1`, `ap-southeast-1`, `ap-southeast-2`, `ca-central-1`, `eu-central-1`, `eu-west-2`, `eu-west-3`, `sa-east-1`, `us-east-1`, `us-east-2`, `us-west-2`
  </Expandable>
</ParamField>

<ParamField path="aws_secret_access_key" type="str" default="''">
  Your AWS Secret Access Key
</ParamField>

## `llm_anthropic_vision`

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").llm_anthropic_vision(api_key="...", image=..., json_schema="...")
  ```
</CodeGroup>

**Parameters**

<ParamField path="use_personal_api_key" type="bool" default="False" />

<ParamField path="json_response" type="bool" default="False" />

<ParamField path="model" type="str" default="'claude-3-haiku-20240307'" />

<ParamField path="prompt" type="str" default="''" />

<ParamField path="system" type="str" default="''" />

<ParamField path="api_key" type="str" required />

<ParamField path="image" type="AcceptsImage" required />

<ParamField path="json_schema" type="str" required />

<ParamField path="sampling" type="SamplingConfig" />

<ParamField path="max_tokens" type="int" />

<ParamField path="temperature" type="float" />

<ParamField path="top_p" type="float" />

## `llm_google_vision`

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").llm_google_vision(prompt="...", api_key="...", image=...)
  ```
</CodeGroup>

**Parameters**

<ParamField path="model" type="str" default="'gemini-pro-vision'" />

<ParamField path="prompt" type="str" required />

<ParamField path="api_key" type="str" required />

<ParamField path="image" type="AcceptsImage" required />

<ParamField path="json_response" type="bool" default="False" />

<ParamField path="provider" type="str" default="'googleImageToText'" />

<ParamField path="stream" type="bool" default="False" />

<ParamField path="sampling" type="SamplingConfig" />

## `llm_open_ai_vision`

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").llm_open_ai_vision(prompt="...", system="...", api_key="...", image=...)
  ```
</CodeGroup>

**Parameters**

<ParamField path="provider" type="str" default="'openAiImageToText'" />

<ParamField path="stream" type="bool" default="False" />

<ParamField path="use_personal_api_key" type="bool" default="False" />

<ParamField path="json_response" type="bool" default="False" />

<ParamField path="model" type="str" default="'gpt-4-vision-preview'">
  <Expandable title="Allowed values">
    `MiniMaxAI/MiniMax-M2.5`, `MiniMaxAI/MiniMax-M2.7`, `Qwen/QwQ-32B-Preview`, `Qwen/Qwen2.5-72B-Instruct-Turbo-lora`, `Qwen/Qwen2.5-7B-Instruct-Turbo`, `Qwen/Qwen3-235B-A22B-Instruct-2507-tput`, `Qwen/Qwen3-235B-A22B-fp8-tput`, `Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8`, `Qwen/Qwen3-VL-8B-Instruct`, `Qwen/Qwen3.5-397B-A17B`, `Qwen/Qwen3.5-9B`, `Qwen/Qwen3.6-Plus`, `accounts/fireworks/models/deepseek-v4-pro`, `accounts/fireworks/models/glm-5p1`, `accounts/fireworks/models/gpt-oss-120b`, `accounts/fireworks/models/kimi-k2p5`, `accounts/fireworks/models/kimi-k2p6`, `accounts/fireworks/models/minimax-m2p7`, `accounts/fireworks/models/qwen3-235b-a22b`, `accounts/fireworks/models/qwen3p5-397b-a17b`, `accounts/fireworks/models/qwen3p6-plus`, `amazon.nova-lite-v1:0`, `amazon.nova-micro-v1:0`, `amazon.nova-pro-v1:0`, `amazon.titan-text-express-v1`, `amazon.titan-text-lite-v1`, `chatgpt-4o-latest`, `claude-3-5-haiku-20241022`, `claude-3-7-sonnet-20250219`, `claude-3-haiku-20240307`, `claude-haiku-4-5-20251001`, `claude-opus-4-1-20250805`, `claude-opus-4-20250514`, `claude-opus-4-5-20251101`, `claude-opus-4-6`, `claude-opus-4-7`, `claude-opus-4-8`, `claude-sonnet-4-20250514`, `claude-sonnet-4-5`, `claude-sonnet-4-6`, `command-nightly`, `command-r-08-2024`, `command-r-plus-08-2024`, `deepcogito/cogito-v2-1-671b`, `deepseek-ai/DeepSeek-R1-Distill-Llama-70B`, `deepseek-ai/DeepSeek-V3`, `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/deepseek-llm-67b-chat`, `gemini-2.0-flash-001`, `gemini-2.0-flash-lite-preview-02-05`, `gemini-2.5-flash`, `gemini-2.5-pro`, `gemini-3-flash-preview`, `gemini-3-pro-preview`, `gemini-3.1-flash-lite-preview`, `gemini-3.1-pro-preview`, `gemini-3.5-flash`, `gemma2-9b-it`, `google/gemma-2-27b-it`, `google/gemma-2-9b-it`, `google/gemma-2b-it`, `google/gemma-3n-E4B-it`, `google/gemma-4-31B-it`, `gpt-3.5-turbo`, `gpt-4`, `gpt-4-turbo`, `gpt-4-turbo-2024-04-09`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `gpt-4o`, `gpt-4o-2024-08-06`, `gpt-4o-mini`, `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `gpt-5.1`, `gpt-5.1-codex`, `gpt-5.1-codex-mini`, `gpt-5.2`, `gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.5`, `grok-2`, `grok-2-vision`, `grok-3-beta`, `grok-3-fast-beta`, `grok-3-mini-beta`, `grok-3-mini-fast-beta`, `grok-4`, `grok-4-0629`, `grok-4-0709`, `grok-4-fast-non-reasoning`, `grok-4-fast-reasoning`, `grok-4-latest`, `llama-3.1-8b-instant`, `llama-3.3-70b-versatile`, `meta-llama/Llama-3-70b-chat-hf`, `meta-llama/Llama-3-8b-chat-hf`, `meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo`, `meta-llama/Llama-3.2-3B-Instruct-Turbo`, `meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo`, `meta-llama/Llama-3.3-70B-Instruct-Turbo`, `meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8`, `meta-llama/Llama-4-Scout-17B-16E-Instruct`, `meta-llama/Meta-Llama-3-70B-Instruct-Lite`, `meta-llama/Meta-Llama-3-70B-Instruct-Turbo`, `meta-llama/Meta-Llama-3-8B-Instruct-Lite`, `meta-llama/Meta-Llama-3-8B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo`, `meta.llama3-8b-instruct-v1:0`, `mistralai/Mistral-7B-Instruct-v0.1`, `mistralai/Mistral-7B-Instruct-v0.2`, `mistralai/Mistral-7B-Instruct-v0.3`, `mistralai/Mixtral-8x22B-Instruct-v0.1`, `mistralai/Mixtral-8x7B-Instruct-v0.1`, `mixtral-8x7b-32768`, `moonshotai/Kimi-K2-Instruct`, `moonshotai/Kimi-K2.5`, `moonshotai/Kimi-K2.6`, `o1`, `o3`, `o3-mini`, `o4-mini`, `openai/gpt-oss-120b`, `openai/gpt-oss-20b`, `perplexity-ai/r1-1776`, `r1-1776`, `sonar`, `sonar-deep-research`, `sonar-pro`, `sonar-reasoning-pro`, `us.anthropic.claude-haiku-4-5-20251001-v1:0`, `us.anthropic.claude-opus-4-1-20250805-v1:0`, `us.anthropic.claude-opus-4-5-20251101-v1:0`, `us.anthropic.claude-opus-4-6-v1`, `us.anthropic.claude-sonnet-4-20250514-v1:0`, `us.anthropic.claude-sonnet-4-5-20250929-v1:0`, `us.anthropic.claude-sonnet-4-6`, `us.meta.llama3-1-70b-instruct-v1:0`, `us.meta.llama3-1-8b-instruct-v1:0`, `us.meta.llama3-2-11b-instruct-v1:0`, `us.meta.llama3-2-1b-instruct-v1:0`, `us.meta.llama3-2-3b-instruct-v1:0`, `us.meta.llama3-2-90b-instruct-v1:0`, `zai-org/GLM-4.5-Air-FP8`, `zai-org/GLM-5`, `zai-org/GLM-5.1`
  </Expandable>
</ParamField>

<ParamField path="prompt" type="str" required />

<ParamField path="system" type="str" required />

<ParamField path="api_key" type="str" required />

<ParamField path="image" type="AcceptsImage" required />

<ParamField path="json_schema" type="str" required />

<ParamField path="sampling" type="SamplingConfig" />

<ParamField path="max_tokens" type="int" />

<ParamField path="temperature" type="float" />

<ParamField path="top_p" type="float" />

## `nl_to_sql`

Convert natural language queries to SQL queries.

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").nl_to_sql(text="...", db_dialect="MySQL", schema="...")
  ```
</CodeGroup>

**Parameters**

<ParamField path="model" type="str" default="'gpt-4o'" />

<ParamField path="text" type="str" required />

<ParamField path="db_dialect" type="str" required>
  One of: `MySQL`, `PostgreSQL`, `SQLite3`, `Snowflake`
</ParamField>

<ParamField path="schema" type="str" required />

## `reducto_extract`

Extract structured data from documents using Reducto

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").reducto_extract(json_schema="...", system_prompt="...")
  ```
</CodeGroup>

**Parameters**

<ParamField path="use_personal_api_key" type="bool" default="False">
  Use your own Reducto API key instead of the platform default.
</ParamField>

<ParamField path="return_citations" type="bool" default="False">
  Return citation bounding boxes for extracted fields.
</ParamField>

<ParamField path="api_key" type="str" default="''">
  Your personal Reducto API key.
</ParamField>

<ParamField path="deep_extract" type="bool" default="True">
  Enable agentic deep extraction for higher accuracy. Uses iterative verification against the source material.
</ParamField>

<ParamField path="files" type="AcceptsFileList" default="[]">
  Documents to extract data from (up to 2,500 pages per document).
</ParamField>

<ParamField path="json_schema" type="str" required>
  A JSON schema defining the structure of data to extract. Use descriptive field names.
</ParamField>

<ParamField path="system_prompt" type="str" required>
  Instructions for how the AI should extract and verify data from the documents.
</ParamField>

## `sales_data_enrichment`

Enhance sales data with validation and enrichment processes

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").sales_data_enrichment()
  ```
</CodeGroup>

**Parameters**

<ParamField path="sub_type" type="str" default="''" />

## `scorer`

Assign a numerical score based on predefined criteria to quantitatively assess a given entity.

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").scorer(provider="anthropic", text="...", criteria="...")
  ```
</CodeGroup>

**Parameters**

<ParamField path="justification" type="bool" default="False">
  Include the AI's justification for its score
</ParamField>

<ParamField path="provider" type="str" required>
  The model provider

  <Expandable title="Allowed values">
    `anthropic`, `azure`, `bedrock`, `cohere`, `custom`, `fireworks`, `google`, `groq`, `openai`, `perplexity`, `together`, `xai`
  </Expandable>
</ParamField>

<ParamField path="model" type="str" default="''">
  The specific model for scoring

  <Expandable title="Allowed values">
    `MiniMaxAI/MiniMax-M2.5`, `MiniMaxAI/MiniMax-M2.7`, `Qwen/QwQ-32B-Preview`, `Qwen/Qwen2.5-72B-Instruct-Turbo-lora`, `Qwen/Qwen2.5-7B-Instruct-Turbo`, `Qwen/Qwen3-235B-A22B-Instruct-2507-tput`, `Qwen/Qwen3-235B-A22B-fp8-tput`, `Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8`, `Qwen/Qwen3-VL-8B-Instruct`, `Qwen/Qwen3.5-397B-A17B`, `Qwen/Qwen3.5-9B`, `Qwen/Qwen3.6-Plus`, `accounts/fireworks/models/deepseek-v4-pro`, `accounts/fireworks/models/glm-5p1`, `accounts/fireworks/models/gpt-oss-120b`, `accounts/fireworks/models/kimi-k2p5`, `accounts/fireworks/models/kimi-k2p6`, `accounts/fireworks/models/minimax-m2p7`, `accounts/fireworks/models/qwen3-235b-a22b`, `accounts/fireworks/models/qwen3p5-397b-a17b`, `accounts/fireworks/models/qwen3p6-plus`, `amazon.nova-lite-v1:0`, `amazon.nova-micro-v1:0`, `amazon.nova-pro-v1:0`, `amazon.titan-text-express-v1`, `amazon.titan-text-lite-v1`, `chatgpt-4o-latest`, `claude-3-5-haiku-20241022`, `claude-3-7-sonnet-20250219`, `claude-3-haiku-20240307`, `claude-haiku-4-5-20251001`, `claude-opus-4-1-20250805`, `claude-opus-4-20250514`, `claude-opus-4-5-20251101`, `claude-opus-4-6`, `claude-opus-4-7`, `claude-opus-4-8`, `claude-sonnet-4-20250514`, `claude-sonnet-4-5`, `claude-sonnet-4-6`, `command-nightly`, `command-r-08-2024`, `command-r-plus-08-2024`, `deepcogito/cogito-v2-1-671b`, `deepseek-ai/DeepSeek-R1-Distill-Llama-70B`, `deepseek-ai/DeepSeek-V3`, `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/deepseek-llm-67b-chat`, `gemini-2.0-flash-001`, `gemini-2.0-flash-lite-preview-02-05`, `gemini-2.5-flash`, `gemini-2.5-pro`, `gemini-3-flash-preview`, `gemini-3-pro-preview`, `gemini-3.1-flash-lite-preview`, `gemini-3.1-pro-preview`, `gemini-3.5-flash`, `gemma2-9b-it`, `google/gemma-2-27b-it`, `google/gemma-2-9b-it`, `google/gemma-2b-it`, `google/gemma-3n-E4B-it`, `google/gemma-4-31B-it`, `gpt-3.5-turbo`, `gpt-4`, `gpt-4-turbo`, `gpt-4-turbo-2024-04-09`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `gpt-4o`, `gpt-4o-2024-08-06`, `gpt-4o-mini`, `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `gpt-5.1`, `gpt-5.1-codex`, `gpt-5.1-codex-mini`, `gpt-5.2`, `gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.5`, `grok-2`, `grok-2-vision`, `grok-3-beta`, `grok-3-fast-beta`, `grok-3-mini-beta`, `grok-3-mini-fast-beta`, `grok-4`, `grok-4-0629`, `grok-4-0709`, `grok-4-fast-non-reasoning`, `grok-4-fast-reasoning`, `grok-4-latest`, `llama-3.1-8b-instant`, `llama-3.3-70b-versatile`, `meta-llama/Llama-3-70b-chat-hf`, `meta-llama/Llama-3-8b-chat-hf`, `meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo`, `meta-llama/Llama-3.2-3B-Instruct-Turbo`, `meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo`, `meta-llama/Llama-3.3-70B-Instruct-Turbo`, `meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8`, `meta-llama/Llama-4-Scout-17B-16E-Instruct`, `meta-llama/Meta-Llama-3-70B-Instruct-Lite`, `meta-llama/Meta-Llama-3-70B-Instruct-Turbo`, `meta-llama/Meta-Llama-3-8B-Instruct-Lite`, `meta-llama/Meta-Llama-3-8B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo`, `meta.llama3-8b-instruct-v1:0`, `mistralai/Mistral-7B-Instruct-v0.1`, `mistralai/Mistral-7B-Instruct-v0.2`, `mistralai/Mistral-7B-Instruct-v0.3`, `mistralai/Mixtral-8x22B-Instruct-v0.1`, `mistralai/Mixtral-8x7B-Instruct-v0.1`, `mixtral-8x7b-32768`, `moonshotai/Kimi-K2-Instruct`, `moonshotai/Kimi-K2.5`, `moonshotai/Kimi-K2.6`, `o1`, `o3`, `o3-mini`, `o4-mini`, `openai/gpt-oss-120b`, `openai/gpt-oss-20b`, `perplexity-ai/r1-1776`, `r1-1776`, `sonar`, `sonar-deep-research`, `sonar-pro`, `sonar-reasoning-pro`, `us.anthropic.claude-haiku-4-5-20251001-v1:0`, `us.anthropic.claude-opus-4-1-20250805-v1:0`, `us.anthropic.claude-opus-4-5-20251101-v1:0`, `us.anthropic.claude-opus-4-6-v1`, `us.anthropic.claude-sonnet-4-20250514-v1:0`, `us.anthropic.claude-sonnet-4-5-20250929-v1:0`, `us.anthropic.claude-sonnet-4-6`, `us.meta.llama3-1-70b-instruct-v1:0`, `us.meta.llama3-1-8b-instruct-v1:0`, `us.meta.llama3-2-11b-instruct-v1:0`, `us.meta.llama3-2-1b-instruct-v1:0`, `us.meta.llama3-2-3b-instruct-v1:0`, `us.meta.llama3-2-90b-instruct-v1:0`, `zai-org/GLM-4.5-Air-FP8`, `zai-org/GLM-5`, `zai-org/GLM-5.1`
  </Expandable>
</ParamField>

<ParamField path="text" type="str" required>
  The text that will be scored
</ParamField>

<ParamField path="additional_context" type="str" default="''">
  Provide any additional context or instructions
</ParamField>

<ParamField path="criteria" type="str" required>
  The criteria that the text will be scored
</ParamField>

<ParamField path="sampling" type="SamplingConfig" />

<ParamField path="max_tokens" type="Any" />

<ParamField path="temperature" type="Any" />

<ParamField path="top_p" type="Any" />

## `speech_to_text`

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").speech_to_text(audio=...)
  ```
</CodeGroup>

**Parameters**

<ParamField path="model" type="str" default="'OpenAI Whisper'">
  One of: `Deepgram`, `OpenAI Whisper`
</ParamField>

<ParamField path="audio" type="AcceptsAudio" required />

<ParamField path="submodel" type="str" default="'nova-2'" />

<ParamField path="tier" type="str" default="'general'" />

## `summarizer`

Summarize large texts using AI.

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").summarizer(provider="anthropic", text="...")
  ```
</CodeGroup>

**Parameters**

<ParamField path="provider" type="str" required>
  The model provider

  <Expandable title="Allowed values">
    `anthropic`, `aws`, `azure`, `bedrock`, `cohere`, `custom`, `fireworks`, `google`, `groq`, `openai`, `perplexity`, `together`, `xai`
  </Expandable>
</ParamField>

<ParamField path="model" type="str" default="''">
  The specific model for summarization

  <Expandable title="Allowed values">
    `MiniMaxAI/MiniMax-M2.5`, `MiniMaxAI/MiniMax-M2.7`, `Qwen/QwQ-32B-Preview`, `Qwen/Qwen2.5-72B-Instruct-Turbo-lora`, `Qwen/Qwen2.5-7B-Instruct-Turbo`, `Qwen/Qwen3-235B-A22B-Instruct-2507-tput`, `Qwen/Qwen3-235B-A22B-fp8-tput`, `Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8`, `Qwen/Qwen3-VL-8B-Instruct`, `Qwen/Qwen3.5-397B-A17B`, `Qwen/Qwen3.5-9B`, `Qwen/Qwen3.6-Plus`, `accounts/fireworks/models/deepseek-v4-pro`, `accounts/fireworks/models/glm-5p1`, `accounts/fireworks/models/gpt-oss-120b`, `accounts/fireworks/models/kimi-k2p5`, `accounts/fireworks/models/kimi-k2p6`, `accounts/fireworks/models/minimax-m2p7`, `accounts/fireworks/models/qwen3-235b-a22b`, `accounts/fireworks/models/qwen3p5-397b-a17b`, `accounts/fireworks/models/qwen3p6-plus`, `amazon.nova-lite-v1:0`, `amazon.nova-micro-v1:0`, `amazon.nova-pro-v1:0`, `amazon.titan-text-express-v1`, `amazon.titan-text-lite-v1`, `chatgpt-4o-latest`, `claude-3-5-haiku-20241022`, `claude-3-7-sonnet-20250219`, `claude-3-haiku-20240307`, `claude-haiku-4-5-20251001`, `claude-opus-4-1-20250805`, `claude-opus-4-20250514`, `claude-opus-4-5-20251101`, `claude-opus-4-6`, `claude-opus-4-7`, `claude-opus-4-8`, `claude-sonnet-4-20250514`, `claude-sonnet-4-5`, `claude-sonnet-4-6`, `command-nightly`, `command-r-08-2024`, `command-r-plus-08-2024`, `deepcogito/cogito-v2-1-671b`, `deepseek-ai/DeepSeek-R1-Distill-Llama-70B`, `deepseek-ai/DeepSeek-V3`, `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/deepseek-llm-67b-chat`, `gemini-2.0-flash-001`, `gemini-2.0-flash-lite-preview-02-05`, `gemini-2.5-flash`, `gemini-2.5-pro`, `gemini-3-flash-preview`, `gemini-3-pro-preview`, `gemini-3.1-flash-lite-preview`, `gemini-3.1-pro-preview`, `gemini-3.5-flash`, `gemma2-9b-it`, `google/gemma-2-27b-it`, `google/gemma-2-9b-it`, `google/gemma-2b-it`, `google/gemma-3n-E4B-it`, `google/gemma-4-31B-it`, `gpt-3.5-turbo`, `gpt-4`, `gpt-4-turbo`, `gpt-4-turbo-2024-04-09`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `gpt-4o`, `gpt-4o-2024-08-06`, `gpt-4o-mini`, `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `gpt-5.1`, `gpt-5.1-codex`, `gpt-5.1-codex-mini`, `gpt-5.2`, `gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.5`, `grok-2`, `grok-2-vision`, `grok-3-beta`, `grok-3-fast-beta`, `grok-3-mini-beta`, `grok-3-mini-fast-beta`, `grok-4`, `grok-4-0629`, `grok-4-0709`, `grok-4-fast-non-reasoning`, `grok-4-fast-reasoning`, `grok-4-latest`, `llama-3.1-8b-instant`, `llama-3.3-70b-versatile`, `meta-llama/Llama-3-70b-chat-hf`, `meta-llama/Llama-3-8b-chat-hf`, `meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo`, `meta-llama/Llama-3.2-3B-Instruct-Turbo`, `meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo`, `meta-llama/Llama-3.3-70B-Instruct-Turbo`, `meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8`, `meta-llama/Llama-4-Scout-17B-16E-Instruct`, `meta-llama/Meta-Llama-3-70B-Instruct-Lite`, `meta-llama/Meta-Llama-3-70B-Instruct-Turbo`, `meta-llama/Meta-Llama-3-8B-Instruct-Lite`, `meta-llama/Meta-Llama-3-8B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo`, `meta.llama3-8b-instruct-v1:0`, `mistralai/Mistral-7B-Instruct-v0.1`, `mistralai/Mistral-7B-Instruct-v0.2`, `mistralai/Mistral-7B-Instruct-v0.3`, `mistralai/Mixtral-8x22B-Instruct-v0.1`, `mistralai/Mixtral-8x7B-Instruct-v0.1`, `mixtral-8x7b-32768`, `moonshotai/Kimi-K2-Instruct`, `moonshotai/Kimi-K2.5`, `moonshotai/Kimi-K2.6`, `o1`, `o3`, `o3-mini`, `o4-mini`, `openai/gpt-oss-120b`, `openai/gpt-oss-20b`, `perplexity-ai/r1-1776`, `r1-1776`, `sonar`, `sonar-deep-research`, `sonar-pro`, `sonar-reasoning-pro`, `us.anthropic.claude-haiku-4-5-20251001-v1:0`, `us.anthropic.claude-opus-4-1-20250805-v1:0`, `us.anthropic.claude-opus-4-5-20251101-v1:0`, `us.anthropic.claude-opus-4-6-v1`, `us.anthropic.claude-sonnet-4-20250514-v1:0`, `us.anthropic.claude-sonnet-4-5-20250929-v1:0`, `us.anthropic.claude-sonnet-4-6`, `us.meta.llama3-1-70b-instruct-v1:0`, `us.meta.llama3-1-8b-instruct-v1:0`, `us.meta.llama3-2-11b-instruct-v1:0`, `us.meta.llama3-2-1b-instruct-v1:0`, `us.meta.llama3-2-3b-instruct-v1:0`, `us.meta.llama3-2-90b-instruct-v1:0`, `zai-org/GLM-4.5-Air-FP8`, `zai-org/GLM-5`, `zai-org/GLM-5.1`
  </Expandable>
</ParamField>

<ParamField path="text" type="str" required>
  The text to be summarized
</ParamField>

<ParamField path="sampling" type="SamplingConfig" />

<ParamField path="max_tokens" type="Any" />

<ParamField path="temperature" type="Any" />

<ParamField path="top_p" type="Any" />

## `translator`

Translate text from one language to another.

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").translator(provider="anthropic", text="...")
  ```
</CodeGroup>

**Parameters**

<ParamField path="provider" type="str" required>
  The model provider

  <Expandable title="Allowed values">
    `anthropic`, `azure`, `bedrock`, `cohere`, `custom`, `fireworks`, `google`, `groq`, `openai`, `perplexity`, `together`, `xai`
  </Expandable>
</ParamField>

<ParamField path="model" type="str" default="''">
  The specific model for translation

  <Expandable title="Allowed values">
    `MiniMaxAI/MiniMax-M2.5`, `MiniMaxAI/MiniMax-M2.7`, `Qwen/QwQ-32B-Preview`, `Qwen/Qwen2.5-72B-Instruct-Turbo-lora`, `Qwen/Qwen2.5-7B-Instruct-Turbo`, `Qwen/Qwen3-235B-A22B-Instruct-2507-tput`, `Qwen/Qwen3-235B-A22B-fp8-tput`, `Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8`, `Qwen/Qwen3-VL-8B-Instruct`, `Qwen/Qwen3.5-397B-A17B`, `Qwen/Qwen3.5-9B`, `Qwen/Qwen3.6-Plus`, `accounts/fireworks/models/deepseek-v4-pro`, `accounts/fireworks/models/glm-5p1`, `accounts/fireworks/models/gpt-oss-120b`, `accounts/fireworks/models/kimi-k2p5`, `accounts/fireworks/models/kimi-k2p6`, `accounts/fireworks/models/minimax-m2p7`, `accounts/fireworks/models/qwen3-235b-a22b`, `accounts/fireworks/models/qwen3p5-397b-a17b`, `accounts/fireworks/models/qwen3p6-plus`, `amazon.nova-lite-v1:0`, `amazon.nova-micro-v1:0`, `amazon.nova-pro-v1:0`, `amazon.titan-text-express-v1`, `amazon.titan-text-lite-v1`, `chatgpt-4o-latest`, `claude-3-5-haiku-20241022`, `claude-3-7-sonnet-20250219`, `claude-3-haiku-20240307`, `claude-haiku-4-5-20251001`, `claude-opus-4-1-20250805`, `claude-opus-4-20250514`, `claude-opus-4-5-20251101`, `claude-opus-4-6`, `claude-opus-4-7`, `claude-opus-4-8`, `claude-sonnet-4-20250514`, `claude-sonnet-4-5`, `claude-sonnet-4-6`, `command-nightly`, `command-r-08-2024`, `command-r-plus-08-2024`, `deepcogito/cogito-v2-1-671b`, `deepseek-ai/DeepSeek-R1-Distill-Llama-70B`, `deepseek-ai/DeepSeek-V3`, `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/deepseek-llm-67b-chat`, `gemini-2.0-flash-001`, `gemini-2.0-flash-lite-preview-02-05`, `gemini-2.5-flash`, `gemini-2.5-pro`, `gemini-3-flash-preview`, `gemini-3-pro-preview`, `gemini-3.1-flash-lite-preview`, `gemini-3.1-pro-preview`, `gemini-3.5-flash`, `gemma2-9b-it`, `google/gemma-2-27b-it`, `google/gemma-2-9b-it`, `google/gemma-2b-it`, `google/gemma-3n-E4B-it`, `google/gemma-4-31B-it`, `gpt-3.5-turbo`, `gpt-4`, `gpt-4-turbo`, `gpt-4-turbo-2024-04-09`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `gpt-4o`, `gpt-4o-2024-08-06`, `gpt-4o-mini`, `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `gpt-5.1`, `gpt-5.1-codex`, `gpt-5.1-codex-mini`, `gpt-5.2`, `gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.5`, `grok-2`, `grok-2-vision`, `grok-3-beta`, `grok-3-fast-beta`, `grok-3-mini-beta`, `grok-3-mini-fast-beta`, `grok-4`, `grok-4-0629`, `grok-4-0709`, `grok-4-fast-non-reasoning`, `grok-4-fast-reasoning`, `grok-4-latest`, `llama-3.1-8b-instant`, `llama-3.3-70b-versatile`, `meta-llama/Llama-3-70b-chat-hf`, `meta-llama/Llama-3-8b-chat-hf`, `meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo`, `meta-llama/Llama-3.2-3B-Instruct-Turbo`, `meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo`, `meta-llama/Llama-3.3-70B-Instruct-Turbo`, `meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8`, `meta-llama/Llama-4-Scout-17B-16E-Instruct`, `meta-llama/Meta-Llama-3-70B-Instruct-Lite`, `meta-llama/Meta-Llama-3-70B-Instruct-Turbo`, `meta-llama/Meta-Llama-3-8B-Instruct-Lite`, `meta-llama/Meta-Llama-3-8B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo`, `meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo`, `meta.llama3-8b-instruct-v1:0`, `mistralai/Mistral-7B-Instruct-v0.1`, `mistralai/Mistral-7B-Instruct-v0.2`, `mistralai/Mistral-7B-Instruct-v0.3`, `mistralai/Mixtral-8x22B-Instruct-v0.1`, `mistralai/Mixtral-8x7B-Instruct-v0.1`, `mixtral-8x7b-32768`, `moonshotai/Kimi-K2-Instruct`, `moonshotai/Kimi-K2.5`, `moonshotai/Kimi-K2.6`, `o1`, `o3`, `o3-mini`, `o4-mini`, `openai/gpt-oss-120b`, `openai/gpt-oss-20b`, `perplexity-ai/r1-1776`, `r1-1776`, `sonar`, `sonar-deep-research`, `sonar-pro`, `sonar-reasoning-pro`, `us.anthropic.claude-haiku-4-5-20251001-v1:0`, `us.anthropic.claude-opus-4-1-20250805-v1:0`, `us.anthropic.claude-opus-4-5-20251101-v1:0`, `us.anthropic.claude-opus-4-6-v1`, `us.anthropic.claude-sonnet-4-20250514-v1:0`, `us.anthropic.claude-sonnet-4-5-20250929-v1:0`, `us.anthropic.claude-sonnet-4-6`, `us.meta.llama3-1-70b-instruct-v1:0`, `us.meta.llama3-1-8b-instruct-v1:0`, `us.meta.llama3-2-11b-instruct-v1:0`, `us.meta.llama3-2-1b-instruct-v1:0`, `us.meta.llama3-2-3b-instruct-v1:0`, `us.meta.llama3-2-90b-instruct-v1:0`, `zai-org/GLM-4.5-Air-FP8`, `zai-org/GLM-5`, `zai-org/GLM-5.1`
  </Expandable>
</ParamField>

<ParamField path="text" type="str" required>
  The text to be translated
</ParamField>

<ParamField path="source_language" type="str" default="'Detect Language'">
  The language of the input text

  <Expandable title="Allowed values">
    `Afrikaans`, `Albanian`, `Amharic`, `Arabic`, `Armenian`, `Assamese`, `Aymara`, `Azerbaijani`, `Bambara`, `Basque`, `Belarusian`, `Bengali`, `Bhojpuri`, `Bosnian`, `Bulgarian`, `Catalan`, `Cebuano`, `Chichewa`, `Chinese Simplified`, `Chinese Traditional`, `Corsican`, `Croatian`, `Czech`, `Danish`, `Detect Language`, `Divehi`, `Dogri`, `Dutch`, `English`, `Esperanto`, `Estonian`, `Ewe`, `Filipino`, `Finnish`, `French`, `Frisian`, `Galician`, `Ganda`, `Georgian`, `German`, `Greek`, `Guarani`, `Gujarati`, `Haitian Creole`, `Hausa`, `Hawaiian`, `Hebrew`, `Hindi`, `Hmong`, `Hungarian`, `Icelandic`, `Igbo`, `Iloko`, `Indonesian`, `Irish Gaelic`, `Italian`, `Japanese`, `Javanese`, `Kannada`, `Kazakh`, `Khmer`, `Kinyarwanda`, `Konkani`, `Korean`, `Krio`, `Kurdish [Kurmanji]`, `Kurdish [Sorani]`, `Kyrgyz`, `Lao`, `Latin`, `Latvian`, `Lingala`, `Lithuanian`, `Luxembourgish`, `Macedonian`, `Maithili`, `Malagasy`, `Malay`, `Malayalam`, `Maltese`, `Maori`, `Marathi`, `Meiteilon Manipuri`, `Mizo`, `Mongolian`, `Myanmar [Burmese]`, `Nepali`, `Northern Sotho`, `Norwegian`, `Odia Oriya`, `Oromo`, `Pashto`, `Persian`, `Polish`, `Portuguese`, `Punjabi`, `Quechua`, `Romanian`, `Russian`, `Samoan`, `Sanskrit`, `Scots Gaelic`, `Serbian`, `Sesotho`, `Shona`, `Sindhi`, `Sinhala`, `Slovak`, `Slovenian`, `Somali`, `Spanish`, `Sundanese`, `Swahili`, `Swedish`, `Tajik`, `Tamil`, `Tatar`, `Telugu`, `Thai`, `Tigrinya`, `Tsonga`, `Turkish`, `Turkmen`, `Twi`, `Ukrainian`, `Urdu`, `Uyghur`, `Uzbek`, `Vietnamese`, `Welsh`, `Xhosa`, `Yiddish`, `Yoruba`, `Zulu`
  </Expandable>
</ParamField>

<ParamField path="target_language" type="str" default="'English'">
  The language to translate to

  <Expandable title="Allowed values">
    `Afrikaans`, `Albanian`, `Amharic`, `Arabic`, `Armenian`, `Assamese`, `Aymara`, `Azerbaijani`, `Bambara`, `Basque`, `Belarusian`, `Bengali`, `Bhojpuri`, `Bosnian`, `Bulgarian`, `Catalan`, `Cebuano`, `Chichewa`, `Chinese Simplified`, `Chinese Traditional`, `Corsican`, `Croatian`, `Czech`, `Danish`, `Divehi`, `Dogri`, `Dutch`, `English`, `Esperanto`, `Estonian`, `Ewe`, `Filipino`, `Finnish`, `French`, `Frisian`, `Galician`, `Ganda`, `Georgian`, `German`, `Greek`, `Guarani`, `Gujarati`, `Haitian Creole`, `Hausa`, `Hawaiian`, `Hebrew`, `Hindi`, `Hmong`, `Hungarian`, `Icelandic`, `Igbo`, `Iloko`, `Indonesian`, `Irish Gaelic`, `Italian`, `Japanese`, `Javanese`, `Kannada`, `Kazakh`, `Khmer`, `Kinyarwanda`, `Konkani`, `Korean`, `Krio`, `Kurdish [Kurmanji]`, `Kurdish [Sorani]`, `Kyrgyz`, `Lao`, `Latin`, `Latvian`, `Lingala`, `Lithuanian`, `Luxembourgish`, `Macedonian`, `Maithili`, `Malagasy`, `Malay`, `Malayalam`, `Maltese`, `Maori`, `Marathi`, `Meiteilon Manipuri`, `Mizo`, `Mongolian`, `Myanmar [Burmese]`, `Nepali`, `Northern Sotho`, `Norwegian`, `Odia Oriya`, `Oromo`, `Pashto`, `Persian`, `Polish`, `Portuguese`, `Punjabi`, `Quechua`, `Romanian`, `Russian`, `Samoan`, `Sanskrit`, `Scots Gaelic`, `Serbian`, `Sesotho`, `Shona`, `Sindhi`, `Sinhala`, `Slovak`, `Slovenian`, `Somali`, `Spanish`, `Sundanese`, `Swahili`, `Swedish`, `Tajik`, `Tamil`, `Tatar`, `Telugu`, `Thai`, `Tigrinya`, `Tsonga`, `Turkish`, `Turkmen`, `Twi`, `Ukrainian`, `Urdu`, `Uyghur`, `Uzbek`, `Vietnamese`, `Welsh`, `Xhosa`, `Yiddish`, `Yoruba`, `Zulu`
  </Expandable>
</ParamField>

## `tts_eleven_labs`

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").tts_eleven_labs(text="...", api_key="...")
  ```
</CodeGroup>

**Parameters**

<ParamField path="model" type="str" default="'eleven_multilingual_v2'" />

<ParamField path="text" type="str" required />

<ParamField path="api_key" type="str" required />

<ParamField path="voice" type="str" default="'shimmer'" />

## `tts_open_ai`

<CodeGroup>
  ```python Sync theme={"languages":{}}
  pipeline.add(name="node").tts_open_ai(text="...", api_key="...")
  ```
</CodeGroup>

**Parameters**

<ParamField path="use_personal_api_key" type="bool" default="False" />

<ParamField path="model" type="str" default="'tts-1-hd'" />

<ParamField path="text" type="str" required />

<ParamField path="api_key" type="str" required />

<ParamField path="voice" type="str" default="'alloy'" />