API Compatibility
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.
01
Sign up & get API key
Create your account at cloud.infercom.ai.
02
Change base URL
Point your existing OpenAI or Anthropic SDK to api.infercom.ai
03
Choose your model
Use gpt-oss-120b (our fastest), Gemma 4 31B (text and images), or any other 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="gpt-oss-120b",
messages=[{"role": "user", "content": "Hello"}],
stream=True
)
for chunk in response:
print(chunk.choices[0].delta.content, end="")from openai import OpenAI
client = OpenAI(
base_url="https://api.infercom.ai/v1",
api_key="your-api-key"
)
# Responses API - built for agentic workflows
response = client.responses.create(
model="gpt-oss-120b",
input="Hello",
reasoning={"effort": "high"}
)
print(response.output_text)from anthropic import Anthropic
client = Anthropic(
base_url="https://api.infercom.ai",
api_key="your-api-key"
)
response = client.messages.create(
model="gpt-oss-120b",
max_tokens=1024,
messages=[{"role": "user", "content": "Hello"}]
)
print(response.content[0].text)curl https://api.infercom.ai/v1/chat/completions \
-H "Authorization: Bearer your-api-key" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-oss-120b",
"messages": [{"role": "user", "content": "Hello"}],
"stream": true
}'Choose Your SDK
Full compatibility with OpenAI and Anthropic client libraries
OpenAI SDK
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 SDK
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 gpt-oss-120b
- Same authentication patterns
Vision, extended thinking, and prompt caching are not currently supported.
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: 'gpt-oss-120b',
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="gpt-oss-120b"
)
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.
Output Throughput, p50, 10K input / 1K output, single request. Last measured: July 2026.
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.
- EU sovereign models run in a certified data center in Munich
- No US CLOUD Act exposure
- GDPR compliant, ISO 27001 certified
- No persistent storage of prompts or outputs