Code with Claude Opus 4.8
in AdaL
Anthropic's newest Opus upgrade is built for better collaboration, reliability, and judgment on complex work. Use it in AdaL CLI and Desktop for repo-aware coding, research, review, and agentic engineering tasks.
Get StartedRun /model and pick Claude Opus 4.8 from the new category · $5/M input · $25/M output tokens
Why use Opus 4.8 in AdaL
A practical upgrade for developers who need stronger judgment, tool use, and long-session reliability
Sharper coding judgment
Anthropic reports Opus 4.8 is more reliable on agentic tasks, asks better questions, catches mistakes, and pushes back when a plan is not sound.
More honest about code quality
In Anthropic evaluations, Opus 4.8 is around 4× less likely than its predecessor to let flaws in code it wrote pass unremarked.
Stronger multimodal work
Partner feedback highlights better reasoning over PDFs, diagrams, dense filings, and other unstructured content.
Improved alignment profile
Anthropic says Opus 4.8 shows substantially lower rates of misaligned behavior than Opus 4.7, with the full assessment in the official model card.
Built for long sessions
Early testers describe richer, more information-dense outputs and better signal-to-noise across long-running analysis work.
Same regular pricing
Regular usage is unchanged from Opus 4.7: $5 per million input tokens and $25 per million output tokens.
How to pick Claude Opus 4.8
Available in AdaL CLI and Desktop through the model selector
Open AdaL CLI or AdaL Desktop
Use the environment where you already plan, code, and review with AdaL.
Run /model
Open the model selector and choose Claude Opus 4.8 from the new category.
Start your hardest coding task
Ask AdaL to inspect the repo, plan the smallest safe change, edit, test, and show the diff.
What early testers reported
Selected quotes from Anthropic's Opus 4.8 launch announcement
"On CursorBench, Claude Opus 4.8 exceeds prior Opus models across every effort level. Tool calling is meaningfully more efficient."
Cursor
"The new Opus model unlocks a step change in agentic reasoning, tackling deeper, multistep questions faster than any prior Opus."
Databricks
"Claude Opus 4.8 delivers the same strong quality as Opus 4.7 with noticeably better citation precision and more token efficiency on retrieval."
Hebbia
"It improves on Opus 4.6 and fixes the comment-verbosity and tool-calling issues we saw with Opus 4.7."
Cognition
Source: Anthropic launch announcement and official Claude Opus 4.8 system card.
Ready to try Opus 4.8 in AdaL?
Open AdaL CLI or Desktop, run /model, and choose Claude Opus 4.8 from the new category.
Get Started with AdaL