OpenAI-Compatible API.
Zero Code Changes.
Switch from OpenAI or Anthropic in minutes. Same SDKs, same code, up to 10x faster inference on EU sovereign infrastructure.
Switch in 5 Minutes
Change one line of code. Keep everything else.
Sign up & get API key
Create your account at cloud.infercom.ai.
Change base URL
Point your existing OpenAI or Anthropic SDK to api.infercom.ai
Choose your model
Use MiniMax M2.7 Ultraspeed (flagship), gpt-oss-120b (fastest), or any model from our catalog.
from openai import OpenAI
client = OpenAI(
base_url="https://api.infercom.ai/v1",
api_key="your-api-key"
)
response = client.chat.completions.create(
model="MiniMax-M2.7",
messages=[{"role": "user", "content": "Hello"}],
stream=True
)
for chunk in response:
print(chunk.choices[0].delta.content, end="")Choose Your SDK
Full compatibility with OpenAI and Anthropic client libraries
OpenAI SDK Compatible
Drop-in replacement for OpenAI. Works with your existing code, tools, and frameworks.
- Chat Completions and Responses API
- Works with LangChain, LlamaIndex, CrewAI
- Python, JavaScript, TypeScript, REST
- Streaming, function calling, JSON mode
Anthropic Messages API
Use the Anthropic SDK directly. Same Messages API format, EU hosted.
- Standard /v1/messages endpoint
- Works with existing Anthropic code
- Tool use on MiniMax and gpt-oss-120b
- Same authentication patterns
Vision, extended thinking, and prompt caching are not currently supported.
View Anthropic compatibility docsModel-Specific Guides
Detailed setup instructions for specific models
More Examples
Works with your favorite languages and frameworks
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.infercom.ai/v1',
apiKey: 'your-api-key',
});
const response = await client.chat.completions.create({
model: 'MiniMax-M2.7',
messages: [{ role: 'user', content: 'Hello' }],
});
console.log(response.choices[0].message.content);from langchain_openai import ChatOpenAI
llm = ChatOpenAI(
base_url="https://api.infercom.ai/v1",
api_key="your-api-key",
model="MiniMax-M2.7"
)
response = llm.invoke("Explain quantum computing")
print(response.content)Faster Than the Alternatives
SambaNova's dataflow architecture delivers up to 10x faster inference than GPU-based providers.
Supported Endpoints
/v1/chat/completionsChat completions with streaming support
/v1/responsesResponses API for agentic workflows - tools, reasoning, streaming
/v1/messagesAnthropic Messages API format
/v1/modelsList available models and metadata
/v1/embeddingsText embeddings (selected models)
EU Sovereignty Included
OpenAI-compatible API, European jurisdiction.
- All inference in Germany (Equinix MU4)
- No US CLOUD Act exposure
- GDPR compliant, ISO 27001 certified
- Zero data retention