Skip to main content

Pydantic AI integration for PathCourse Health — typed agents with autonomous USDC billing on Base L2

Project description

pydantic-ai-pathcourse

Pydantic AI integration for PathCourse Health. Build typed, production-grade agents with autonomous USDC billing on Base L2 — no accounts, no credit cards, no KYC.

Install

pip install pydantic-ai-pathcourse

Quick Start

from pydantic_ai import Agent
from pydantic_ai_pathcourse import PathCourseModel

agent = Agent(
    model=PathCourseModel("pch-pro"),
    system_prompt="You are an expert in autonomous agent infrastructure.",
)

result = agent.run_sync("What is Path Score?")
print(result.data)

Structured output

Pydantic AI's structured-output guarantees work unchanged with PCH:

from pydantic import BaseModel
from pydantic_ai import Agent
from pydantic_ai_pathcourse import PathCourseModel


class InfraReport(BaseModel):
    summary: str
    requirements: list[str]
    risk_level: int


agent = Agent(
    model=PathCourseModel("pch-pro"),
    result_type=InfraReport,
)

result = agent.run_sync("Analyze autonomous agent infrastructure for a fintech startup.")
print(result.data.requirements)

Tool use

from pydantic_ai import Agent, RunContext
from pydantic_ai_pathcourse import PathCourseModel

agent = Agent(model=PathCourseModel("pch-pro"))

@agent.tool
async def get_balance(ctx: RunContext[None], agent_id: str) -> float:
    """Look up the USDC balance for a PCH agent."""
    return 42.50

result = agent.run_sync("What is the balance for agent abc123?")

Models

Model Rate Min tier Notes
pch-fast $0.44 / M tokens uncertified Fast reasoning, classification, routing
pch-coder $3.50 / M tokens uncertified Code generation, debugging
pch-embed $0.015 / M tokens uncertified Text embeddings for semantic search / RAG
pch-translate $0.08 / M chars uncertified Multilingual translation
pch-pro $1.96 / M tokens bronze Deep reasoning, multi-step planning
pch-audio $1.85 / M chars bronze Text-to-speech, standard quality
pch-documents $0.26 in / $1.48 out per M tokens bronze Document parsing / OCR
pch-transcribe $0.0008 / minute bronze Speech-to-text
pch-extract $0.012 / M tokens bronze Structured data extraction
pch-rerank $0.025 / M tokens bronze Reranking for RAG pipelines
pch-image $0.028 / image silver Text-to-image
pch-audio-premium $37.00 / M chars silver Text-to-speech, premium quality
pch-talk $0.001 / minute silver Voice conversation
claude-haiku Common rate silver Anthropic Claude Haiku
claude-sonnet Common rate gold Anthropic Claude Sonnet

PathCourseModel only operates on chat-completion shapes — for image/audio/transcription, use the PCH Python SDK directly.

Choosing a chat model:

  • Fast response, simple task → pch-fast
  • Complex reasoning, multi-step → pch-pro
  • Writing or reviewing code → pch-coder
  • Long context or premium reasoning → claude-sonnet (Gold tier)

Authentication

Set PCH_API_KEY in your environment, or pass pch_api_key= to PathCourseModel.

export PCH_API_KEY=pch_prod_b_...

Developer access — $5 USDC. Send $5+ USDC on Base (chain ID 8453) to the PCH treasury wallet, then call pathcourse.claim_key(tx_hash, wallet) to retrieve your key. No accounts, no credit card, no KYC. $5 buys thousands of pch-fast calls — enough to verify any typed-agent integration. Top up to $25 lifetime and your account auto-upgrades to Uncertified with pch-coder access. Treasury address: see payment.treasury_wallet in /.well-known/agent.json.

Links

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pydantic_ai_pathcourse-0.1.2.tar.gz (3.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

pydantic_ai_pathcourse-0.1.2-py3-none-any.whl (4.0 kB view details)

Uploaded Python 3

File details

Details for the file pydantic_ai_pathcourse-0.1.2.tar.gz.

File metadata

  • Download URL: pydantic_ai_pathcourse-0.1.2.tar.gz
  • Upload date:
  • Size: 3.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.3

File hashes

Hashes for pydantic_ai_pathcourse-0.1.2.tar.gz
Algorithm Hash digest
SHA256 c3517bf0d0ba315378a22a0a8a616280fd1b0cff7976803a54b93995040a3ca8
MD5 8199d92c01aaa3d178e3c8bc31155f54
BLAKE2b-256 282393247c6f674a6ef603e99e04ebd9928c4f928b631985838dc495b6c68a68

See more details on using hashes here.

File details

Details for the file pydantic_ai_pathcourse-0.1.2-py3-none-any.whl.

File metadata

File hashes

Hashes for pydantic_ai_pathcourse-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 a042ea94ef89657d90707a6dd047b58c823c14cc4f05ccda2c39c4e05f07ccf0
MD5 4cf1eb807a769d4b6fdba27e63e5e476
BLAKE2b-256 30449cff2ce8475a89bef2bba448a1a3ac2c16916492918516b2538ce2b54ff4

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page