Claude Opus 4.5 Now Available in Cline
Claude Opus 4.5 is now in Cline with 80.9% SWE-bench performance and up to 65% fewer tokens. $5/$15 per million tokens, 200K context.
TL;DR
- Claude Opus 4.5 is now available in Cline with 80.9% SWE-bench Verified performance
- Up to 65% fewer tokens than previous models on comparable tasks — better efficiency for long sessions
- $5/$15 per million tokens (input/output) with 200K context window; available now as
claude-opus-4-5
What Dropped
Anthropic's Claude Opus 4.5 is live in Cline. This is the company's most capable model yet, built for complex, multi-step coding problems where reasoning and tool orchestration matter. It's not a minor update — it's a meaningful step up in capability.
The Dev Angle
Opus 4.5 hits 80.9% on SWE-bench Verified and 59.3% on Terminal-bench 2.0. More importantly: it uses dramatically fewer tokens to get there. In Anthropic's testing, at medium effort Opus 4.5 matches Sonnet 4.5's best SWE-bench score while using 76% fewer output tokens. At high effort, it exceeds Sonnet 4.5 by 4.3 percentage points while using 48% fewer tokens.
For Cline workflows, this compounds. Longer sessions, more work done per dollar. The model "just gets it" on complex, multi-system bugs — tasks that were near-impossible for Sonnet 4.5 are now within reach. Heavy MCP usage with multiple tools orchestrated together? This is where Opus 4.5 shines.
Pricing is $5 per million input tokens and $15 per million output tokens. The 200K context window gives you room to work with larger codebases and longer conversation histories.
Should You Care?
If you're running straightforward coding tasks, Sonnet 4.5 remains the right call — it's fast, capable, and cost-effective for day-to-day work. Stick with it.
If you're hitting walls on complex problems — ambiguous bugs across multiple systems, heavy tool orchestration, reasoning-heavy tasks — Opus 4.5 is worth switching to. The token efficiency means the cost premium often pays for itself on longer sessions. The model's reasoning capability is genuinely better.
For teams already using Cline with faster model switching, this makes it easier to reach for the right tool at the right time. Use Sonnet for quick fixes, Opus for the hard problems.
Source: Cline