Follow Discord
Sweep 31 Oct 2026 · 01:10Z Build v2.1.316 534 read Stable v2.1.309 Latest v2.1.316 Next v2.1.316 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One change · api

pdf-support changedbuild-with-claude/pdf-support

Nearest release: v2.1.315, published under an hour before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+5added
Lines−44removed
From line 34 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits21to this page, all time

### Amazon Bedrock PDF support #### Document processing modes #### Key limitations #### Common issues

The whole hunk

from line 34, old and new numbered
/
lines
from line 34
3434 note: Base64 sources only.
3535 Amazon Bedrock (InvokeModel):
3636 availability: ga
37 note: Base64 sources only. With the Converse API, visual PDF analysis needs citations turned on.
37 note: Base64 sources only.
3838 Claude Models on Google Cloud (Google managed):
3939 availability: ga
4040 note: Base64 sources only.
from line 72
7272 
7373### Supported platforms and models
7474 
75All [active models](https://platform.claude.com/docs/en/models/overview) support PDF processing. For PDF support through Amazon Bedrock’s Converse API, see [Amazon Bedrock PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support#amazon-bedrock-pdf-support).
75All [active models](https://platform.claude.com/docs/en/models/overview) support PDF processing.
7676 
77### Amazon Bedrock PDF support
78 
79When using PDF support through the Converse API, part of [Claude on Amazon Bedrock (Opus 4.6 and earlier)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), there are two distinct document processing modes:
80 
8177<Note>
82 **Important:** To access Claude’s full visual PDF understanding capabilities in the Converse API, you must enable citations. Without citations enabled, the API falls back to basic text extraction only. Learn more about [working with citations](https://platform.claude.com/docs/en/build-with-claude/citations).
83</Note>
84 
85#### Document processing modes
86 
871. **Converse Document Chat** (Original mode - Text extraction only)
88 
89 * Provides basic text extraction from PDFs
90 * Cannot analyze images, charts, or visual layouts within PDFs
91 * Uses approximately 1,000 tokens for a 3-page PDF
92 * Automatically used when citations are not enabled
93 
942. **Claude PDF Chat** (New mode - Full visual understanding)
95 
96 * Provides complete visual analysis of PDFs
97 * Can understand and analyze charts, graphs, images, and visual layouts
98 * Processes each page as both text and image for comprehensive understanding
99 * Uses approximately 7,000 tokens for a 3-page PDF
100 * **Requires citations to be enabled** in the Converse API
101 
102#### Key limitations
103 
104* **Converse API:** Visual PDF analysis requires citations to be enabled. There is currently no option to use visual analysis without citations (unlike the InvokeModel API).
105* **InvokeModel API:** Provides full control over PDF processing without forced citations.
106 
107#### Common issues
108 
109If Claude isn’t seeing images or charts in your PDFs when using the Converse API, you likely need to enable the citations flag. Without it, Converse falls back to basic text extraction only.
110 
111<Note>
112 This is a known constraint with the Converse API. For applications that require visual PDF analysis without citations, consider using the InvokeModel API instead.
113</Note>
114 
115<Note>
11678 Plain text files such as .txt, .csv, or .md can be used directly in document blocks: upload them to the Files API with MIME type `text/plain` and reference them by `file_id`. Binary formats such as .xlsx or .docx are not supported in document blocks, so convert them to text or PDF first. See [Working with other file formats](https://platform.claude.com/docs/en/build-with-claude/files#working-with-other-file-formats).
11779</Note>
11880 
from line 1031
10691031 
10701032The token count of a PDF file depends on the total text extracted from the document and the number of pages:
10711033 
1072* Text token costs: Each page typically uses 1,500–3,000 tokens per page depending on content density. Standard API pricing applies with no additional PDF fees.
1034* Text token costs: Each page typically uses 1,500–3,000 tokens depending on content density. Standard API pricing applies with no additional PDF fees.
10731035* Image token costs: Because each page is converted into an image, the same [image-based cost calculations](https://platform.claude.com/docs/en/build-with-claude/vision#evaluate-image-size) are applied.
10741036 
10751037You can use [token counting](https://platform.claude.com/docs/en/build-with-claude/token-counting) to estimate costs for your specific PDFs.
from line 1994
20321994| Available | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |
20331995| Available<sup>1</sup> | [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
20341996| Available<sup>2</sup> | [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) |
2035| Available<sup>3</sup> | [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) |
1997| Available<sup>2</sup> | [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) |
20361998 
203719991. `file_id` sources need a Hosted on Anthropic deployment.
20382. Base64 sources only. With the Converse API, visual PDF analysis needs citations turned on.
20393. Base64 sources only.
20002. Base64 sources only.
20402001 
20412002#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
20422003 
Feedback