OpenAI-compatible API

Use PublicaAI from your code

PublicaAI exposes a drop-in OpenAI-compatible endpoint backed by Anthropic Claude on AWS Bedrock. Point any OpenAI SDK or LangChain client at our base URL with your staff key — that's it.

Base URL

https://bedrock.publicaai.com

Auth header

Authorization: Bearer sk-…

Available models

Model ID	Description	Cost multiplier	Max tokens
`claude-4-5-haiku`	Fast, low cost	1×	4,000
`claude-4-5-sonnet`	Balanced performance	3×	4,000

Credit cost: (input_tokens + output_tokens × 5) × cost_multiplier × 1.2. Output tokens are 5× more expensive than input tokens.

Quickstart

Install the OpenAI SDK and point it at PublicaAI:

bash

pip install openai

python

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-publicaai-key",     # your staff API key
    base_url="https://bedrock.publicaai.com/v1",
)

response = client.chat.completions.create(
    model="claude-4-5-sonnet",
    messages=[
        {"role": "user", "content": "Summarise our company values in 3 bullets."},
    ],
    max_tokens=500,
)

print(response.choices[0].message.content)
print(f"Credits remaining: {response.usage.credits_remaining}")

Other endpoints

GET

/v1/models

Lists every model available to your key, with cost multipliers and limits.

GET

/v1/usage

Returns your remaining credits, 24h usage breakdown and per-model statistics.

Limits & responses

Rate limit

requests / minute / key

Max tokens

4,000

per request

Insufficient credits

402

HTTP status returned