Required prerequisites
Motivation
CAMEL already talks to any OpenAI-compatible host via ModelPlatformType.OPENAI_COMPATIBLE_MODEL (https://docs.camel-ai.org/key_modules/models). People looking for prepaid, privacy-first inference still have to guess the host, key format, and that the parameter is url (not base_url).
A named PZERO example on that page, same shape as the OpenRouter sample, would let users paste and run. No first-party CAMEL platform enum required.
Solution
import os
from camel.agents import ChatAgent
from camel.models import ModelFactory
from camel.types import ModelPlatformType
model = ModelFactory.create(
model_platform=ModelPlatformType.OPENAI_COMPATIBLE_MODEL,
model_type="deepseek-v4-flash",
url="https://api.pzero.studio/v1",
api_key=os.environ["PZERO_API_KEY"],
model_config_dict={"temperature": 0.2},
)
agent = ChatAgent(
system_message="Reply in one sentence.",
model=model,
)
response = agent.step("Hello from PZERO")
print(response.msg.content)
url is the /v1 root, not /v1/chat/completions. Pass the catalog id as-is. Keep api_mode at the default chat_completions unless you have verified the Responses path.
Get a key: https://pzero.studio/agents (sign-in free; min top-up 1 USDC on Base; no starter credits). Live text ids: GET https://api.pzero.studio/v1/models (public, no key). Default landing model: deepseek-v4-flash.
Smoke against the same host CAMEL will call:
curl -sS -X POST "https://api.pzero.studio/v1/chat/completions" \
-H "Authorization: Bearer $PZERO_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-v4-flash","messages":[{"role":"user","content":"Hello from PZERO"}],"stream":false}'
I am not asking for a bundled ModelPlatformType.PZERO. The existing OpenAI-compatible seam is enough.
Alternatives
A first-party platform enum next to OpenRouter / Groq. Nice later. Not required for users today.
Pointing at Venice's own host (https://api.venice.ai/api/v1). Wrong product. PZERO is a prepaid marketplace in front of that upstream.
Additional context
Every AI Credit is at least 20% off $1 list. Usage is paid. Do not start implementation on my behalf until the board says Ready; the snippet is for users today.
Required prerequisites
Motivation
CAMEL already talks to any OpenAI-compatible host via
ModelPlatformType.OPENAI_COMPATIBLE_MODEL(https://docs.camel-ai.org/key_modules/models). People looking for prepaid, privacy-first inference still have to guess the host, key format, and that the parameter isurl(notbase_url).A named PZERO example on that page, same shape as the OpenRouter sample, would let users paste and run. No first-party CAMEL platform enum required.
Solution
urlis the/v1root, not/v1/chat/completions. Pass the catalog id as-is. Keepapi_modeat the defaultchat_completionsunless you have verified the Responses path.Get a key: https://pzero.studio/agents (sign-in free; min top-up 1 USDC on Base; no starter credits). Live text ids:
GET https://api.pzero.studio/v1/models(public, no key). Default landing model:deepseek-v4-flash.Smoke against the same host CAMEL will call:
I am not asking for a bundled
ModelPlatformType.PZERO. The existing OpenAI-compatible seam is enough.Alternatives
A first-party platform enum next to OpenRouter / Groq. Nice later. Not required for users today.
Pointing at Venice's own host (
https://api.venice.ai/api/v1). Wrong product. PZERO is a prepaid marketplace in front of that upstream.Additional context
Every AI Credit is at least 20% off $1 list. Usage is paid. Do not start implementation on my behalf until the board says Ready; the snippet is for users today.