OpenAI-compatible, Anthropic-compatible, and Gemini AI Studio native protocols are all supported for text generation.
OpenAI-Compatible Interface For features not covered here, refer to the OpenAI API Reference .
Message Roles Role Purpose Example systemSets the model’s behavior and persona ”You are an experienced software engineer.” userThe end user’s input ”How do I reverse a string in Python?” assistantPrior model responses, for multi-turn context ”You can use s[::-1] or ''.join(reversed(s)).”
Basic Conversation from openai import OpenAI client = OpenAI( base_url = "https://api.ephone.ai/v1" , api_key = "API_KEY" , ) response = client.chat.completions.create( model = "gpt-4o" , messages = [{ "role" : "user" , "content" : "Hello!" }] ) print (response.choices[ 0 ].message.content)
Streaming from openai import OpenAI client = OpenAI( base_url = "https://api.ephone.ai/v1" , api_key = "API_KEY" , ) stream = client.chat.completions.create( model = "gpt-4o" , messages = [{ "role" : "user" , "content" : "Write a short poem about spring." }], stream = True , ) for chunk in stream: if chunk.choices[ 0 ].delta.content: print (chunk.choices[ 0 ].delta.content, end = "" , flush = True )
For more details, see the OpenAI tool use guide .
from openai import OpenAI client = OpenAI( base_url = "https://api.ephone.ai/v1" , api_key = "API_KEY" , ) tools = [ { "type" : "function" , "function" : { "name" : "get_weather" , "description" : "Get the current weather for a city" , "parameters" : { "type" : "object" , "properties" : { "city" : { "type" : "string" , "description" : "City name" } }, "required" : [ "city" ], }, }, } ] response = client.chat.completions.create( model = "gpt-4o" , messages = [{ "role" : "user" , "content" : "What's the weather in London?" }], tools = tools, ) print (response.choices[ 0 ].message)
Response API The OpenAI Responses API is supported for OpenAI models. See the OpenAI Responses API docs for usage details.
Set OPENAI_BASE_URL to https://api.ephone.ai/v1
Set OPENAI_API_KEY to your API key
Some parameters (presence_penalty, frequency_penalty, logit_bias, etc.) may be ignored by certain models
The legacy function_call parameter is deprecated — use tools instead
Anthropic-Compatible Interface For features not covered here, refer to the Anthropic API Reference .
Basic Conversation import anthropic client = anthropic.Anthropic( base_url = "https://api.ephone.ai/anthropic" , api_key = "API_KEY" , ) message = client.messages.create( model = "claude-opus-4-5-20251101" , max_tokens = 1024 , messages = [{ "role" : "user" , "content" : "Hello!" }] ) print (message.content[ 0 ].text)
Streaming import anthropic client = anthropic.Anthropic( base_url = "https://api.ephone.ai/anthropic" , api_key = "API_KEY" , ) with client.messages.stream( model = "claude-opus-4-5-20251101" , max_tokens = 1024 , messages = [{ "role" : "user" , "content" : "Write a short poem about spring." }], ) as stream: for text in stream.text_stream: print (text, end = "" , flush = True )
For more details, see the Anthropic tool use guide .
import anthropic client = anthropic.Anthropic( base_url = "https://api.ephone.ai/anthropic" , api_key = "API_KEY" , ) tools = [ { "name" : "get_weather" , "description" : "Get the current weather for a city" , "input_schema" : { "type" : "object" , "properties" : { "city" : { "type" : "string" , "description" : "City name" } }, "required" : [ "city" ], }, } ] message = client.messages.create( model = "claude-opus-4-5-20251101" , max_tokens = 1024 , tools = tools, messages = [{ "role" : "user" , "content" : "What's the weather in London?" }], ) print (message.content)
Set ANTHROPIC_BASE_URL to https://api.ephone.ai/anthropic
Set ANTHROPIC_API_KEY to your API key
Gemini AI Studio Compatible Interface Gemini models support direct calls using the official Google AI Studio API format — no conversion to OpenAI format required. Ideal for projects already using the Google genai SDK.
For features not covered here, refer to the Google AI Studio API Reference .
Basic Conversation from google import genai from google.genai import types client = genai.Client( api_key = "API_KEY" , http_options = types.HttpOptions( api_version = "v1beta" , base_url = "https://api.ephone.ai" , ), ) response = client.models.generate_content( model = "gemini-2.5-pro" , contents = "Hello!" , ) print (response.text)
Streaming from google import genai from google.genai import types client = genai.Client( api_key = "API_KEY" , http_options = types.HttpOptions( api_version = "v1beta" , base_url = "https://api.ephone.ai" , ), ) for chunk in client.models.generate_content_stream( model = "gemini-2.5-pro" , contents = "Write a short poem about spring." , ): print (chunk.text, end = "" , flush = True )
For more details, see the Google AI Studio function calling guide .
from google import genai from google.genai import types client = genai.Client( api_key = "API_KEY" , http_options = types.HttpOptions( api_version = "v1beta" , base_url = "https://api.ephone.ai" , ), ) get_weather = types.FunctionDeclaration( name = "get_weather" , description = "Get the current weather for a city" , parameters = types.Schema( type = "OBJECT" , properties = { "city" : types.Schema( type = "STRING" , description = "City name" ), }, required = [ "city" ], ), ) response = client.models.generate_content( model = "gemini-2.5-pro" , contents = "What's the weather in London?" , config = types.GenerateContentConfig( tools = [types.Tool( function_declarations = [get_weather])] ), ) print (response.candidates[ 0 ].content.parts)
Set base_url / baseUrl to https://api.ephone.ai (without /v1beta suffix — the SDK appends it automatically)
Set api_version / apiVersion to v1beta
Set api_key / apiKey to your API key
Install dependencies: Python pip install google-genai, Node.js npm install @google/genai
OpenAI Official Docs OpenAI Chat Completions API reference
Anthropic Official Docs Anthropic Messages API reference
Google AI Studio Docs Gemini GenerateContent API reference