Skip to content

guanyang/open-agent-hub / skills/claude-api

claude-api

Unverified

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

FileKindSize
LICENSE.txtmarkdown11.1 KB
SKILL.mdskill md102.7 KB
csharp/claude-api.mdmarkdown15.3 KB
csharp/claude-api/README.mdmarkdown18.5 KB
csharp/claude-api/batches.mdmarkdown413 B
csharp/claude-api/files-api.mdmarkdown900 B
csharp/claude-api/streaming.mdmarkdown787 B
csharp/claude-api/tool-use.mdmarkdown7.4 KB
curl/examples.mdmarkdown9.5 KB
curl/managed-agents.mdmarkdown10.5 KB
go/claude-api.mdmarkdown14.4 KB
go/claude-api/README.mdmarkdown8.3 KB
go/claude-api/files-api.mdmarkdown936 B
go/claude-api/streaming.mdmarkdown1.0 KB
go/claude-api/tool-use.mdmarkdown9.8 KB
go/managed-agents/README.mdmarkdown21.9 KB
java/claude-api.mdmarkdown15.5 KB
java/claude-api/README.mdmarkdown11.7 KB
java/claude-api/files-api.mdmarkdown1.2 KB
java/claude-api/streaming.mdmarkdown655 B
java/claude-api/tool-use.mdmarkdown10.9 KB
java/managed-agents/README.mdmarkdown20.0 KB
php/claude-api.mdmarkdown11.5 KB
php/claude-api/README.mdmarkdown6.4 KB
php/claude-api/batches.mdmarkdown447 B
php/claude-api/files-api.mdmarkdown476 B
php/claude-api/streaming.mdmarkdown682 B
php/claude-api/tool-use.mdmarkdown9.5 KB
php/managed-agents/README.mdmarkdown16.2 KB
python/agent-sdk/README.mdmarkdown12.4 KB
python/agent-sdk/patterns.mdmarkdown9.0 KB
python/claude-api/README.mdmarkdown20.1 KB
python/claude-api/batches.mdmarkdown5.6 KB
python/claude-api/files-api.mdmarkdown4.4 KB
python/claude-api/sdk-upgrade.mdmarkdown28.1 KB
python/claude-api/streaming.mdmarkdown11.7 KB
python/claude-api/tool-use.mdmarkdown20.9 KB
python/managed-agents/README.mdmarkdown14.5 KB
ruby/claude-api.mdmarkdown3.4 KB
ruby/claude-api/README.mdmarkdown4.7 KB
ruby/claude-api/streaming.mdmarkdown235 B
ruby/claude-api/tool-use.mdmarkdown2.6 KB
ruby/managed-agents/README.mdmarkdown11.9 KB
shared/admin-api.mdmarkdown11.3 KB
shared/agent-design.mdmarkdown8.5 KB
shared/anthropic-cli.mdmarkdown23.4 KB
shared/claude-platform-on-aws.mdmarkdown4.3 KB
shared/cost-optimization.mdmarkdown57.1 KB
shared/error-codes.mdmarkdown20.3 KB
shared/evals/build-eval.mdmarkdown53.5 KB
shared/evals/cost-hillclimb.mdmarkdown31.0 KB
shared/evals/eval-audit.mdmarkdown27.2 KB
shared/evals/eval-hillclimb.mdmarkdown67.5 KB
shared/evals/report/SCHEMA.mdmarkdown15.7 KB
shared/evals/report/build-report-lite.mjsscript26.7 KB
shared/evals/report/runner-scaffold.mjsscript32.4 KB
shared/live-sources.mdmarkdown17.3 KB
shared/managed-agents-api-reference.mdmarkdown34.5 KB
shared/managed-agents-client-patterns.mdmarkdown11.8 KB
shared/managed-agents-core.mdmarkdown32.7 KB
shared/managed-agents-environments.mdmarkdown13.9 KB
shared/managed-agents-events.mdmarkdown25.4 KB
shared/managed-agents-memory.mdmarkdown11.1 KB
shared/managed-agents-multiagent.mdmarkdown65.1 KB
shared/managed-agents-onboarding-from-quickstart.mdmarkdown19.3 KB
shared/managed-agents-onboarding-from-url.mdmarkdown31.9 KB
shared/managed-agents-onboarding.mdmarkdown16.4 KB
shared/managed-agents-outcomes.mdmarkdown8.8 KB
shared/managed-agents-overview.mdmarkdown14.2 KB
shared/managed-agents-quickstarts/bug-hunter.mdmarkdown7.9 KB
shared/managed-agents-quickstarts/contract-tracker.mdmarkdown1.8 KB
shared/managed-agents-quickstarts/data-analyst.mdmarkdown1.5 KB
shared/managed-agents-quickstarts/deep-researcher.mdmarkdown2.4 KB
shared/managed-agents-quickstarts/explainer-video-maker.mdmarkdown4.8 KB
shared/managed-agents-quickstarts/field-monitor.mdmarkdown2.1 KB
shared/managed-agents-quickstarts/incident-commander.mdmarkdown1.7 KB
shared/managed-agents-quickstarts/performance-tuner.mdmarkdown11.1 KB
shared/managed-agents-quickstarts/sprint-retro-facilitator.mdmarkdown2.0 KB
shared/managed-agents-quickstarts/structured-extractor.mdmarkdown1.5 KB
shared/managed-agents-quickstarts/support-agent.mdmarkdown1.4 KB
shared/managed-agents-quickstarts/support-to-eng-escalator.mdmarkdown1.8 KB
shared/managed-agents-quickstarts/watchlist-scanner.mdmarkdown5.5 KB
shared/managed-agents-scheduled-deployments.mdmarkdown9.3 KB
shared/managed-agents-self-hosted-sandboxes.mdmarkdown27.3 KB
shared/managed-agents-tools.mdmarkdown37.0 KB
shared/managed-agents-webhooks.mdmarkdown11.1 KB
shared/model-migration.mdmarkdown338.1 KB
shared/models.mdmarkdown17.1 KB
shared/platform-availability.mdmarkdown7.2 KB
shared/preserved-thinking-migration.mdmarkdown62.5 KB
shared/preserved-thinking-migration/causes.mdmarkdown38.8 KB
shared/preserved-thinking-migration/drop_block_probe.pyscript65.0 KB
shared/preserved-thinking-migration/prefix_diff.pyscript91.8 KB
shared/prompt-audit.mdmarkdown48.2 KB
shared/prompt-caching.mdmarkdown32.3 KB
shared/token-counting.mdmarkdown1.6 KB
shared/tool-use-concepts.mdmarkdown43.3 KB
typescript/agent-sdk/README.mdmarkdown10.6 KB
typescript/agent-sdk/patterns.mdmarkdown4.6 KB
typescript/claude-api/README.mdmarkdown15.5 KB
typescript/claude-api/batches.mdmarkdown2.5 KB
typescript/claude-api/files-api.mdmarkdown2.3 KB
typescript/claude-api/streaming.mdmarkdown9.3 KB
typescript/claude-api/tool-use.mdmarkdown23.7 KB
typescript/managed-agents/README.mdmarkdown13.7 KB

python/claude-api/files-api.md

View on GitHub
# Files API - Python

The Files API uploads files for use in Messages API requests. Reference files via `file_id` in content blocks, avoiding re-uploads across multiple API calls.

The Files API is out of beta. In current SDKs `client.beta.files` has breaking shape changes from previous versions, matching the stable `client.files` - migrate per the Files API row in `shared/live-sources.md`. Examples below predate this.

## Key Facts

- Maximum file size: 500 MB
- Total storage: 100 GB per organization
- Files persist until deleted
- File operations (upload, list, delete) are free; content used in messages is billed as input tokens
- Not available on Amazon Bedrock or Google Vertex AI

---

## Upload a File

The `file` argument accepts a `(filename, content, content_type)` tuple, a `pathlib.Path` (or any `PathLike` - read for you, async-safe with `AsyncAnthropic`), or an open binary file object.

```python
import anthropic
from pathlib import Path

client = anthropic.Anthropic()

uploaded = client.beta.files.upload(
    file=("report.pdf", open("report.pdf", "rb"), "application/pdf"),
)
# or: client.beta.files.upload(file=Path("report.pdf"))
print(f"File ID: {uploaded.id}")
print(f"Size: {uploaded.size_bytes} bytes")
```

---

## Use a File in Messages

### PDF / Text Document

```python
response = client.beta.messages.create(
    model="claude-opus-5-5",
    max_tokens=16000,
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Summarize the key findings in this report."},
            {
                "type": "document",
                "source": {"type": "file", "file_id": uploaded.id},
                "title": "Q4 Report",           # optional
                "citations": {"enabled": True}   # optional, enables citations
            }
        ]
    }],
    betas=["files-api-2025-04-14"],
)
for block in response.content:
    if block.type == "text":
        print(block.text)
```

### Image

```python
image_file = client.beta.files.upload(
    file=("photo.png", open("photo.png", "rb"), "image/png"),
)

response = client.beta.messages.create(
    model="claude-opus-5-5",
    max_tokens=16000,
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "What's in this image?"},
            {
                "type": "image",
                "source": {"type": "file", "file_id": image_file.id}
            }
        ]
    }],
    betas=["files-api-2025-04-14"],
)
```

---

## Manage Files

### List Files

Iterate the list result directly - the SDK auto-paginates across all pages. Only use `.data` if you want the first page only.

```python
for f in client.beta.files.list():
    print(f"{f.id}: {f.filename} ({f.size_bytes} bytes)")
```

### Get File Metadata

```python
file_info = client.beta.files.retrieve_metadata("file_011CNha8iCJcU1wXNR6q4V8w")
print(f"Filename: {file_info.filename}")
print(f"MIME type: {file_info.mime_type}")
```

### Delete a File

```python
client.beta.files.delete("file_011CNha8iCJcU1wXNR6q4V8w")
```

### Download a File

Only files created by the code execution tool or skills can be downloaded (not user-uploaded files).

```python
file_content = client.beta.files.download("file_011CNha8iCJcU1wXNR6q4V8w")
file_content.write_to_file("output.txt")
```

---

## Full End-to-End Example

Upload a document once, ask multiple questions about it:

```python
import anthropic

client = anthropic.Anthropic()

# 1. Upload once
uploaded = client.beta.files.upload(
    file=("contract.pdf", open("contract.pdf", "rb"), "application/pdf"),
)
print(f"Uploaded: {uploaded.id}")

# 2. Ask multiple questions using the same file_id
questions = [
    "What are the key terms and conditions?",
    "What is the termination clause?",
    "Summarize the payment schedule.",
]

for question in questions:
    response = client.beta.messages.create(
        model="claude-opus-5-5",
        max_tokens=16000,
        messages=[{
            "role": "user",
            "content": [
                {"type": "text", "text": question},
                {
                    "type": "document",
                    "source": {"type": "file", "file_id": uploaded.id}
                }
            ]
        }],
        betas=["files-api-2025-04-14"],
    )
    print(f"\nQ: {question}")
    text = next((b.text for b in response.content if b.type == "text"), "")
    print(f"A: {text[:200]}")

# 3. Clean up when done
client.beta.files.delete(uploaded.id)
```
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall