OCI GenAI us-chicago-1 (ORD) · 17 Verified Models · OpenAI Wire Compatible
One OpenAI-compatible gateway for Grok 4, Gemini 2.5, Llama 4, GPT-OSS & Cohere v4
Point LangChain, LlamaIndex, Cursor, OpenAI Python/Node SDKs, or PHP cURL at a single base URL. Pure-PHP 8.3 OCI RSA-SHA256 signing routes Chat, 1536-dim Embeddings, and Rerank in us-chicago-1 with live SSE streaming and atomic RPM/RPD enforcement.
Base URL
https://api.topseotoolkit.com/v1
Active OCI Regional Pool
ORD
Live
us-chicago-1
US Midwest (Chicago) · 17 verified models
Measured info2431 Benchmarks (us-chicago-1)
100/100
Concurrent · 0 dropped
~23/s
Sustained · 0.70s p50
1536d
Cohere Embed v4.0
17
Chat + Embed + Rerank
Verified Model Catalog (17)
On-demand verified models in us-chicago-1 (15 Chat + Cohere Embed v4.0 + Cohere Rerank v4.0 Fast).
| Model ID | Display Name | Type | Tier | Context | Region Pool |
|---|---|---|---|---|---|
google.gemini-2.5-flash-lite
|
Gemini 2.5 Flash Lite | chat | fast | 1,000,000 |
us-chicago-1
|
google.gemini-2.5-flash
|
Gemini 2.5 Flash | chat | balanced | 1,000,000 |
us-chicago-1
|
google.gemini-2.5-pro
|
Gemini 2.5 Pro | chat | premium | 1,000,000 |
us-chicago-1
|
xai.grok-4.7
|
Grok 4.7 | chat | premium | 131,072 |
us-chicago-1
|
xai.grok-4.6
|
Grok 4.6 | chat | premium | 131,072 |
us-chicago-1
|
xai.grok-4.3
|
Grok 4.3 | chat | balanced | 131,072 |
us-chicago-1
|
xai.grok-4.20-reasoning
|
Grok 4.20 Reasoning | chat | reasoning | 131,072 |
us-chicago-1
|
xai.grok-4.20-non-reasoning
|
Grok 4.20 Non-Reasoning | chat | fast | 131,072 |
us-chicago-1
|
xai.grok-4.20-0309-reasoning
|
Grok 4.20 (0309) Reasoning | chat | reasoning | 131,072 |
us-chicago-1
|
xai.grok-4.20-0309-non-reasoning
|
Grok 4.20 (0309) Non-Reasoning | chat | fast | 131,072 |
us-chicago-1
|
meta.llama-4-maverick-17b-128e-instruct-fp8
|
Llama 4 Maverick 17B 128E | chat | premium | 131,072 |
us-chicago-1
|
meta.llama-4-scout-17b-16e-instruct
|
Llama 4 Scout 17B 16E | chat | balanced | 131,072 |
us-chicago-1
|
meta.llama-3.3-70b-instruct
|
Llama 3.3 70B Instruct | chat | balanced | 131,072 |
us-chicago-1
|
openai.gpt-oss-120b
|
GPT-OSS 120B | chat | premium | 131,072 |
us-chicago-1
|
openai.gpt-oss-20b
|
GPT-OSS 20B | chat | fast | 131,072 |
us-chicago-1
|
cohere.embed-v4.0
|
Cohere Embed v4.0 | embedding (1536d) | balanced | 128,000 |
us-chicago-1
|
cohere.rerank-v4.0-fast
|
Cohere Rerank v4.0 Fast | rerank | fast | 32,768 |
us-chicago-1
|
OpenAI SDK Quickstart
curl -sS https://api.topseotoolkit.com/v1/chat/completions \
-H "Authorization: Bearer sk-fleet-YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "xai.grok-4.7",
"messages": [{"role": "user", "content": "Hello from OCI us-chicago-1!"}],
"stream": true
}'
from openai import OpenAI
client = OpenAI(base_url="https://api.topseotoolkit.com/v1", api_key="sk-fleet-YOUR_KEY")
resp = client.chat.completions.create(
model="xai.grok-4.7",
messages=[{"role": "user", "content": "Hello from Python!"}],
)
print(resp.choices[0].message.content)
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.topseotoolkit.com/v1", apiKey: "sk-fleet-YOUR_KEY" });
const res = await client.chat.completions.create({
model: "meta.llama-4-maverick-17b-128e-instruct-fp8",
messages: [{ role: "user", content: "Hello from Node.js!" }],
});
console.log(res.choices[0].message.content);
$ch = curl_init("https://api.topseotoolkit.com/v1/chat/completions");
curl_setopt_array($ch, [
CURLOPT_POST => true,
CURLOPT_RETURNTRANSFER => true,
CURLOPT_HTTPHEADER => [
"Authorization: Bearer sk-fleet-YOUR_KEY",
"Content-Type: application/json",
],
CURLOPT_POSTFIELDS => json_encode([
"model" => "google.gemini-2.5-flash-lite",
"messages" => [["role" => "user", "content" => "Hello from PHP 8.3!"]],
]),
]);
$response = curl_exec($ch);