GPT-5.4 and GPT-5.4 Pro Are Live on Cencori

OpenAI announced GPT-5.4 and GPT-5.4 Pro on March 5, 2026, and both models are now available on Cencori.

You can use them today with:

• gpt-5.4
• gpt-5.4-pro

For compatibility, Cencori also accepts:

• gpt-5.4-thinking -> normalized to gpt-5.4

Why This Update Matters

GPT-5.4 and GPT-5.4 Pro bring OpenAI's latest reasoning and coding improvements into the same Cencori gateway workflow you already use for security, observability, and model routing.

No API migration is required. If you already call Cencori chat endpoints, switch the model ID and go.

Use It Now

Cencori SDK

import { Cencori } from 'cencori';
 
const cencori = new Cencori({ apiKey: process.env.CENCORI_API_KEY });
 
const response = await cencori.ai.chat({
  model: 'gpt-5.4',
  messages: [
    { role: 'system', content: 'You are a senior engineer.' },
    { role: 'user', content: 'Review this rollout plan and list risks.' }
  ]
});
 
console.log(response.content);

HTTP API

curl -X POST https://cencori.com/api/ai/chat \
  -H "CENCORI_API_KEY: $CENCORI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [
      {"role": "user", "content": "Give me a migration checklist for this architecture."}
    ]
  }'

What We Shipped in Cencori

This rollout is live across the platform:

• model catalog and /api/v1/models
• OpenAI-compatible routing normalization for GPT-5.4 alias compatibility
• fallback mapping for cross-provider failover
• dashboard model pickers (Playground and Logs)
• docs and examples updated

Notes for Production Teams

• gpt-5.4 is the canonical API model ID for GPT-5.4 Thinking.
• If you rely on strict model pinning for long-running evals, keep your own pinned fallback policy.

References

• OpenAI: Introducing GPT-5.4
• Cencori Models Catalog