Claude Opus 5 is on Cencori

Claude Opus 5 is live on Cencori.
Anthropic's new Opus-tier flagship succeeds Claude Opus 4.8 as the recommended default for complex agentic coding and enterprise work — with Anthropic describing it as coming close to the frontier intelligence of Claude Fable 5 at half the price. Opus 4.8 remains fully supported on Cencori if you need to pin to it.
Starting today, you can target claude-opus-5 across our entire unified API Gateway, with all billing trackers and security layers configured automatically.
Introducing Claude Opus 5
Opus 5 is Anthropic's pick for the hardest agentic coding and enterprise workloads — the model to reach for when a task is genuinely complex rather than routine. It supports the same adaptive thinking, vision, tool use, and streaming capabilities as the rest of the current Claude lineup, with a 1,000,000 token context window and up to 128,000 tokens of output per request.
Pricing & Specs
Claude Opus 5 is priced identically to Opus 4.8 — no premium for the upgrade.
| Metric | Value |
|---|---|
| Input Price | $5.00 / million tokens |
| Output Price | $25.00 / million tokens |
| Context Window | 1,000,000 tokens |
| Max Output | 128,000 tokens |
| Model ID | claude-opus-5 |
Powering Claude Opus 5 with Cencori
Integrating new frontier models is trivial when your applications are built on Cencori's intelligence infrastructure:
- Decoupled Billing & Credit Quotas: Cencori manages credit allocations, end-user billing, and budget caps at the proxy level. Switching your workloads to
claude-opus-5doesn't require touching your billing logic — Cencori tracks provider cost and markup automatically at the new model's rates. - Enterprise Security Layer: Cencori's input and output security pipeline — PII detection, jailbreak detection, and custom data rules — applies to Opus 5 traffic the same way it does to every other model on the gateway, with full audit logging.
- Seamless Model Failovers: Opus 5 is now the default Anthropic fallback target for our GPT-5.5 and o3 traffic on Cencori. If your Claude Opus 5 usage hits provider rate limits, traffic can automatically route to GPT-5.5 or Gemini 3.1 Pro Preview without breaking active client sessions.
Using Claude Opus 5 in Cencori
You can begin targeting the new model immediately using our TypeScript SDK:
import { cencori } from 'cencori';
const response = await cencori.chat.create({
model: 'claude-opus-5',
messages: [
{
role: 'user',
content: 'Refactor this service to handle concurrent writes safely.'
}
]
});
Claude Opus 5 is available now for all Cencori customers. Check your Model Catalog to see it in action.