Available models - Unstructured

Partitioner (VLM)

Provider	Model ID
`anthropic`	`claude-opus-4-5-20251101` `claude-opus-4-6` `claude-sonnet-4-20250514` `claude-sonnet-4-5-20250929`
`azure_openai`	`gpt-4o` `gpt-4o-mini` `gpt-5-mini`
`bedrock`	`us.amazon.nova-lite-v1:0` `us.amazon.nova-pro-v1:0` `us.anthropic.claude-3-haiku-20240307-v1:0` `us.anthropic.claude-3-opus-20240229-v1:0` `us.anthropic.claude-3-sonnet-20240229-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`
`openai`	`gpt-4o` `gpt-4o-mini` `gpt-5-mini` `gpt-5.2`
`vertexai`	`gemini-2.0-flash-001` `gemini-2.5-flash` `gemini-2.5-pro`

Embedder

Provider	Model ID
`azure_openai`	`text-embedding-3-large` `text-embedding-3-small` `text-embedding-ada-002`
`bedrock`	`amazon.titan-embed-text-v1` `amazon.titan-embed-text-v2:0` `cohere.embed-english-v3` `cohere.embed-multilingual-v3` `amazon.titan-embed-image-v1`
`ibm`	`sentence-transformers/all-minilm-l6-v2` `ibm/granite-embedding-278m-multilingual` `intfloat/multilingual-e5-large` `ibm/slate-125m-english-rtrvr-v2` `ibm/slate-30m-english-rtrvr-v2`
`togetherai`	`togethercomputer/m2-bert-80M-32k-retrieval`
`voyageai`	`voyage-3` `voyage-3-large` `voyage-3-lite` `voyage-code-2` `voyage-code-3` `voyage-finance-2` `voyage-law-2` `voyage-multimodal-3`

Extract (LLM)

Provider	Model ID
`anthropic`	`claude-opus-4-5-20251101` `claude-sonnet-4-20250514` `claude-sonnet-4-5-20250929`
`azure_openai`	`gpt-4o` `gpt-4o-mini` `gpt-5-mini`
`bedrock`	`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`
`openai`	`gpt-4o` `gpt-4o-mini` `gpt-5-mini`

Enrichment nodes

Generative OCR

Provider	Model ID
`anthropic`	`claude-opus-4-5-20251101` `claude-opus-4-6` `claude-sonnet-4-20250514` `claude-sonnet-4-5-20250929`
`azure_openai`	`gpt-4o` `gpt-4o-mini` `gpt-5-mini`
`bedrock`	`us.amazon.nova-lite-v1:0` `us.amazon.nova-pro-v1:0` `us.anthropic.claude-3-haiku-20240307-v1:0` `us.anthropic.claude-3-opus-20240229-v1:0` `us.anthropic.claude-3-sonnet-20240229-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`
`openai`	`gpt-4o` `gpt-4o-mini` `gpt-5-mini` `gpt-5.2`

Image Description

Provider	Model ID
`anthropic`	`claude-opus-4-5-20251101` `claude-opus-4-6` `claude-sonnet-4-20250514` `claude-sonnet-4-5-20250929`
`azure_openai`	`gpt-4o` `gpt-4o-mini` `gpt-5-mini`
`bedrock`	`us.amazon.nova-lite-v1:0` `us.amazon.nova-pro-v1:0` `us.anthropic.claude-3-haiku-20240307-v1:0` `us.anthropic.claude-3-opus-20240229-v1:0` `us.anthropic.claude-3-sonnet-20240229-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`
`openai`	`gpt-4o` `gpt-4o-mini` `gpt-5-mini` `gpt-5.2`
`vertexai`	`gemini-2.0-flash-001` `gemini-2.5-flash` `gemini-2.5-pro`

Named Entity Recognition

Provider	Model ID
`anthropic`	`claude-opus-4-5-20251101` `claude-opus-4-6` `claude-sonnet-4-20250514` `claude-sonnet-4-5-20250929`
`azure_openai`	`gpt-4o` `gpt-4o-mini` `gpt-5-mini`
`openai`	`gpt-4o` `gpt-4o-mini` `gpt-5-mini` `gpt-5.2`

Table Description

Provider	Model ID
`anthropic`	`claude-opus-4-5-20251101` `claude-opus-4-6` `claude-sonnet-4-20250514` `claude-sonnet-4-5-20250929`
`azure_openai`	`gpt-4o` `gpt-4o-mini` `gpt-5-mini`
`bedrock`	`us.amazon.nova-lite-v1:0` `us.amazon.nova-pro-v1:0` `us.anthropic.claude-3-haiku-20240307-v1:0` `us.anthropic.claude-3-opus-20240229-v1:0` `us.anthropic.claude-3-sonnet-20240229-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`
`openai`	`gpt-4o` `gpt-4o-mini` `gpt-5-mini` `gpt-5.2`
`vertexai`	`gemini-2.0-flash-001` `gemini-2.5-flash` `gemini-2.5-pro`

Table to HTML

Provider	Model ID
`anthropic`	`claude-opus-4-5-20251101` `claude-opus-4-6` `claude-sonnet-4-20250514` `claude-sonnet-4-5-20250929`
`azure_openai`	`gpt-4o` `gpt-4o-mini` `gpt-5-mini`
`bedrock`	`us.amazon.nova-lite-v1:0` `us.amazon.nova-pro-v1:0` `us.anthropic.claude-3-haiku-20240307-v1:0` `us.anthropic.claude-3-opus-20240229-v1:0` `us.anthropic.claude-3-sonnet-20240229-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`
`openai`	`gpt-4o` `gpt-4o-mini` `gpt-5-mini` `gpt-5.2`