Universal API

One API for 200+ LLMs across every major provider. Use OpenAI’s Chat Completions, Responses API, or Anthropic’s Messages format — Portkey translates between them all.

Available on all Portkey plans.

Portkey’s AI Gateway provides a single, unified API for 200+ models from every major provider. Write once in any format, switch providers by changing one parameter.

Three API Formats, Any Provider

Portkey supports three API formats. Each works with all providers — Portkey handles translation automatically.

Chat Completions

OpenAI spec · POST /v1/chat/completions

Widest ecosystem compatibility

Responses API

OpenAI spec · POST /v1/responses

Agentic AI with built-in tool use

Messages API

Anthropic spec · POST /v1/messages

Native Anthropic format across providers

Chat Completions — POST /v1/chat/completions

OpenAI-compatible format with the widest ecosystem support. Full guide →

Portkey Python

from portkey_ai import Portkey

portkey = Portkey(api_key="PORTKEY_API_KEY")

response = portkey.chat.completions.create(
    model="@anthropic-provider/claude-sonnet-4-5-20250514",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

Responses API — POST /v1/responses

OpenAI’s next-gen format for agentic AI with built-in tool use and reasoning. Full guide →

Portkey Python

from portkey_ai import Portkey

portkey = Portkey(api_key="PORTKEY_API_KEY")

response = portkey.responses.create(
    model="@anthropic-provider/claude-sonnet-4-5-20250514",
    input="Hello!"
)

print(response.output_text)

Messages API — POST /v1/messages

Anthropic-native format using the Anthropic SDK pointed at Portkey’s base URL. Full guide →

Python

import anthropic

client = anthropic.Anthropic(
    api_key="PORTKEY_API_KEY",
    base_url="https://api.portkey.ai"
)

message = client.messages.create(
    model="@anthropic-provider/claude-sonnet-4-5-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}]
)

print(message.content[0].text)

The Portkey SDK is a superset of the OpenAI SDK. The OpenAI SDK also works directly — point base_url at https://api.portkey.ai/v1. For the Messages API, use the Anthropic SDK. See Model Catalog for provider setup.

Switching Providers

Change the @provider/model string to switch between any provider. The API format stays the same.

Portkey Python

from portkey_ai import Portkey

portkey = Portkey(api_key="PORTKEY_API_KEY")

# OpenAI
response = portkey.chat.completions.create(
    model="@openai-provider/gpt-4o",
    messages=[{"role": "user", "content": "Hello"}]
)

# Switch to Anthropic -- same client, different model string
response = portkey.chat.completions.create(
    model="@anthropic-provider/claude-sonnet-4-5-20250514",
    messages=[{"role": "user", "content": "Hello"}]
)

# Switch to Gemini
response = portkey.chat.completions.create(
    model="@google-provider/gemini-2.0-flash",
    messages=[{"role": "user", "content": "Hello"}]
)

Set up providers and credentials in the Model Catalog. The @provider-slug in the model string routes requests to the correct provider automatically.

Routing, Fallbacks, and Load Balancing

Configs enable routing strategies, fallbacks, and load balancing across providers.

Portkey Python

from portkey_ai import Portkey

config = {
    "strategy": {"mode": "fallback"},
    "targets": [
        {"override_params": {"model": "@openai-provider/gpt-4o"}},
        {"override_params": {"model": "@anthropic-provider/claude-sonnet-4-5-20250514"}}
    ]
}

portkey = Portkey(api_key="PORTKEY_API_KEY", config=config)

# Automatically falls back to Anthropic if OpenAI fails
response = portkey.chat.completions.create(
    messages=[{"role": "user", "content": "Hello"}]
)

Configs work with all three API formats — Chat Completions, Responses, and Messages.

For more details, see Configs and Conditional Routing.

Local and Private Models

Route to local or private models with custom_host. The model must be compatible with a supported provider format.

Portkey Python

from portkey_ai import Portkey

portkey = Portkey(
    api_key="PORTKEY_API_KEY",
    provider="mistral-ai",
    custom_host="http://MODEL_URL/v1/"
)

response = portkey.chat.completions.create(
    model="mixtral-8x22b",
    messages=[{"role": "user", "content": "Hello"}]
)

Include the version identifier (e.g., /v1) in the custom_host URL. Portkey appends the endpoint path (/chat/completions, /responses, etc.) automatically. For Ollama, see the Ollama integration.

Supported Endpoints

Core Endpoints

• Chat Completions — OpenAI-compatible text generation with streaming, function calling, and multimodal inputs
• Responses API — Next-gen format with built-in tool use and reasoning
• Messages API — Anthropic-compatible endpoint across all providers
• Images — Generate, edit, and create image variations (DALL-E, gpt-image-1, Stable Diffusion)
• Audio — Speech-to-text and text-to-speech

Advanced Capabilities

• Fine-tuning — Customize models on specific datasets
• Batch Processing — Process large request volumes efficiently
• Files — Upload and manage files for fine-tuning and batch operations
• Moderations — Content safety and compliance checks

Additional Endpoints

• Gateway to Other APIs — Proxy requests to any provider endpoint
• Assistants API — OpenAI Assistants with persistent threads
• Completions — Legacy text completion endpoint

Multimodal Capabilities

Multimodal inputs work across all three API formats:

• Vision — Image understanding across providers
• Function Calling — Tool use and function calling
• Image Generation — Text-to-image generation
• Speech-to-Text — Audio transcription
• Text-to-Speech — Audio generation
• Thinking / Reasoning — Extended reasoning modes

Not all providers support every endpoint or modality. See the provider compatibility matrix for details.