AI for everyone.

One API for leading models, with clear provider availability and request-level billing.

Get API Key Explore Models
from openai import OpenAI

client = OpenAI(
    base_url="https://api.kineticrouter.com/v1",
    api_key="YOUR_KINETICROUTER_API_KEY"
)

response = client.chat.completions.create(
    model="openai/gpt-5.4",
    messages=[{"role": "user", "content": "Hello!"}]
)
0.15x–0.30xReference price range
20 modelsDated catalog
snapshot
57 docsStatus-marked
references

Codex WebSocket

  1. 1Get a kineticRouter API Key
  2. 2Configure the kineticRouter provider
  3. 3Validate Responses and WebSocket behavior
# ~/.codex/config.toml
model_provider = "kineticrouter"

[model_providers.kineticrouter]
base_url = "https://api.kineticrouter.com/v1"
wire_api = "responses"
supports_websockets = true
Config~/.codex/config.tomlView available guide

Popular reference prices

Imported snapshot values with route status shown on every card.

View full model pricing

Anthropic: Claude Opus 5

anthropic/claude-opus-5 · Reference

0.2x
SnapshotkineticRouter (0.2x)Official ref.
Input$1/M$5/M
Output$5/M$25/M
Cache read$0.1/M$0.5/M

OpenAI: GPT-5.6 Sol

openai/gpt-5.6-sol · Available

0.15x
SnapshotkineticRouter (0.15x)Official ref.
Input$0.6/M$4/M
Output$3/M$20/M
Cache read$0.06/M$0.4/M

xAI: Grok 4.6

grok/grok-4.6 · Reference

0.15x
SnapshotkineticRouter (0.15x)Official ref.
Input$0.3/M$2/M
Output$0.9/M$6/M
Cache read$0.075/M$0.5/M