OpenAI-compatible
Detected base route
The /v1 surface responds and is suitable for authenticated conformance testing.
Validate the exact model and feature you use
Connect Codex through the OpenAI-compatible API or Claude Code through the available Anthropic-native route. Use your kineticRouter API key to get started.
export KINETICROUTER_API_KEY="YOUR_KINETICROUTER_API_KEY"No universal throughput, latency, uptime, or rate-limit promise is made here. Those values depend on your account and deployment.
OpenAI-compatible
The /v1 surface responds and is suitable for authenticated conformance testing.
Validate the exact model and feature you use
Codex
Configure the Responses provider with an environment-held key, then verify your chosen model. Optional WebSocket behavior requires a separate account test.
Test with your kineticRouter account
Claude models
Connect an OpenAI-compatible client to Claude models with your kineticRouter API key.
Follow the installation and provider setup guides
Configuration reference
# Add this provider alongside your existing configuration.
[model_providers.kineticrouter]
name = "kineticRouter"
base_url = "https://api.kineticrouter.com/v1"
env_key = "KINETICROUTER_API_KEY"
wire_api = "responses"codex -c model_provider="kineticrouter" -m "YOUR_AVAILABLE_MODEL_ID"Choose an available Claude model and use the same OpenAI SDK and base URL as every other provider.
Use your kineticRouter API key with the shared OpenAI-compatible base URL:
https://api.kineticrouter.com/v1Example using the OpenAI SDK:
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.kineticrouter.com/v1",
api_key=os.environ["KINETICROUTER_API_KEY"],
)
response = client.chat.completions.create(
model="anthropic/claude-sonnet-5-5",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)Read available guide Use the customer console for authoritative keys, balance, billing, and account capabilities.
Open console