Code with Claude Opus 4.8 in Kilo Code
Anthropic's most powerful model for professional software engineering. Frontier performance across coding, agents, reasoning, and knowledge work with a 1M token context window.
Why developers choose Opus 4.8
The most powerful model for complex, long-running professional tasks
Better Judgment
Early testers report sharper judgment on agentic tasks: asking better questions, catching mistakes, and pushing back when a plan is not sound.
More Honest Code Work
Anthropic reports Opus 4.8 is around four times less likely than Opus 4.7 to let flaws in code it has written pass unremarked.
Stronger Agentic Reliability
Testers describe Opus 4.8 as more reliable on end-to-end agent workloads, with stronger consistency across complex, multi-step tasks.
More Efficient Tool Use
Cursor's early testing found tool calling meaningfully more efficient, using fewer steps for the same intelligence and carrying end-to-end tasks through.
Benchmark Gains Over Opus 4.7
Opus 4.8 improves on Opus 4.7 across Anthropic's launch benchmarks for coding, terminal tasks, computer use, reasoning, and finance agents.
Same Opus Pricing
Anthropic says regular Opus 4.8 pricing is unchanged from Opus 4.7: $5 per million input tokens and $25 per million output tokens.
Save 20% on select Claude models through Kilo Gateway
Through our collaboration with a stealth provider, Kilo users get 20% off select Claude Opus and Sonnet models when running them through Kilo Gateway.
Try discounted Claude modelsOpus 4.8 Benchmark Performance
Official Anthropic launch benchmarks for coding, agents, reasoning, and knowledge work
| Benchmark | Opus 4.8 | Opus 4.7 | GPT-5.5 | Gemini 3.1 Pro |
|---|---|---|---|---|
| Agentic coding (SWE-Bench Pro) | 69.2% | 64.3% | 58.6% | 54.2% |
| Agentic terminal coding (Terminal-Bench 2.1) | 74.6% | 66.1% | 78.2% | 70.3% |
| Multidisciplinary reasoning (Humanity's Last Exam, no tools) | 49.8% | 46.9% | 41.4% | 44.4% |
| Multidisciplinary reasoning (Humanity's Last Exam, with tools) | 57.9% | 54.7% | 52.2% | 51.4% |
| Agentic computer use (OSWorld-Verified) | 83.4% | 82.8% | 78.7% | 76.2% |
| Knowledge work (GDPval-AA) | 1890 | 1753 | 1769 | 1314 |
| Agentic financial analysis (Finance Agent v2) | 53.9% | 51.5% | 51.8% | 43.0% |
Claude Opus 4.8 in Kilo Code
Explore model details, pricing, and capabilities
How to use Claude Opus 4.8
Get started in minutes
Install Kilo Code
Add Kilo Code extension to VS Code, JetBrains IDE, or use the CLI.
Create a free account
Sign up for free at app.kilo.ai — it takes less than a minute.
Select Claude Opus 4.8
Choose Claude Opus 4.8 from the model picker — available through Kilo Gateway.
Trusted by developers at the world's most innovative companies
Other affordable and free models available in Kilo Code
Not just Opus 4.8 — explore 500+ models including free options and budget-friendly high-performers
Free Models for Everyday Coding
Start building without spending a cent
Nemotron 3 Super
NVIDIA's 120B-parameter open hybrid MoE model — only 12B active per token. Ranks in Kilo's top coding models this week, and it's free.
Ling-2.6-1T
inclusionAI's trillion-parameter flagship instant model, built for fast execution and efficient real-world agent workflows at zero cost.
Ling-2.6-flash
inclusionAI's 104B total / 7.4B active parameter flash model for fast responses, strong execution, and high token efficiency.
Affordable High-Performers
Frontier-level quality at a fraction of the cost
Grok Code Fast 1
The model that powered the free frontier era. Kilo Coders have been using over 700B tokens per month. Now at a remarkably low price point.
MiniMax M3
Long-context multimodal model suited for agentic work, coding, and complex document tasks at a low price point.
GLM 4.7 Flash
30B-class model optimized for agentic coding, long-horizon planning, and high-volume work at a very low input price.
Gemini 3 Flash Preview
Outperforms Gemini 3 Pro on many benchmarks at 1/4 the cost. Excellent for high-volume coding tasks.
Agentic Engineering
Glide through your workflow with a mode for every step
Ask mode
A knowledgeable technical assistant focused on answering questions without changing your codebase
Use Kilo Everywhere
Kilo works where you work. Build alone or with your team.
Frequently Asked Questions
Compare AI models by real usage
See how Claude Opus 4.8 and other coding models rank across Kilo Bench, live usage, mode-specific workflows, pricing, speed, and context windows.
Kilo Bench
Compare model quality, cost, and speed on coding-agent benchmarks.
View leaderboardTop models today
Browse the models developers are using most in Kilo Code right now.
View leaderboardModels by mode
Find the strongest models for Code, Plan, Debug, Ask, and Orchestrator.
View leaderboardBest CLI agents
Compare terminal coding agents for Claude Code, Codex CLI, Gemini CLI, Qwen Code, and Kilo CLI.
View leaderboardReady to code with the most powerful AI model?
Join 3M+ developers using Kilo Code. Experience frontier coding and agentic performance with Claude Opus 4.8.