Maker of the Claude family of frontier models. Anthropic’s coding models on Kilo Code include Claude Opus 4.6, Claude Opus 4.5, Claude Sonnet 4.5, and Claude Haiku 4.5. Use them across VS Code, JetBrains IDEs, Cursor, Windsurf, Trae, and the Kilo CLI — with pay-as-you-go pricing and no markup over the underlying provider rates.
Sorted by coding-index where published. Click any model for the full review with benchmarks, real-world Kilo usage, and provider-specific pricing.
Anthropic
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...
Anthropic
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
Anthropic
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
Anthropic
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
Anthropic
Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...
Anthropic
Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...
Anthropic is an AI safety company founded in 2021 by former OpenAI researchers. Its Claude family is the dominant frontier alternative to GPT for software engineering, with Claude Opus and Claude Sonnet leading SWE-Bench Verified and Terminal-Bench 2.0 across multiple releases. Anthropic does not publish open weights; all access is via API.
Pay-as-you-go, no markup over the underlying provider rates. Cheapest first.
| Model | Input / 1M | Output / 1M | Context | Coding index |
|---|---|---|---|---|
| Anthropic: Claude Haiku 4.5 | $1.00 | $5.00 | 200K | 29.6 |
| Anthropic: Claude Sonnet 4.5 | $3.00 | $15.00 | 1000K | 38.6 |
| Anthropic: Claude Sonnet 4.6 | $3.00 | $15.00 | 1000K | — |
| Anthropic: Claude Opus 4.6 | $5.00 | $25.00 | 1000K | 47.6 |
| Anthropic: Claude Opus 4.5 | $5.00 | $25.00 | 200K | 42.9 |
| Anthropic: Claude Opus 4.7 | $5.00 | $25.00 | 1000K | — |
Two ways: hosted in Kilo with no setup, or through your own provider keys.
The fastest path: install Kilo Code, sign in, pick anthropic from the model picker. No API keys, no markup. Works in VS Code, JetBrains, Cursor, Windsurf, Trae, and the Kilo CLI.
See live model leaderboard →Already have an account with Anthropic, OpenRouter, AWS Bedrock, Google Vertex, Together AI, or another compatible provider? Plug your key into Kilo Code and keep your existing billing relationship.
BYOK setup guide →See coding-model lineups from Anthropic’s closest competitors.
Anthropic’s flagship is among the strongest coding models on the Kilo Code leaderboard, ranked by Code, Plan, Ask, Debug, and Review usage.
VS Code, Cursor, Windsurf, Trae, JetBrains IDEs (IntelliJ, PyCharm, WebStorm, GoLand, RubyMine, Android Studio), and the Kilo CLI / terminal.
Switch between Anthropic and 500+ other models with one click. Pay only for what you use, at the underlying provider rate.
Claude Opus 4.7 is currently the strongest Anthropic coding model on Kilo Code, with Claude Sonnet 4.6 the best speed/cost balance. Opus is the right choice for complex agentic tasks; Sonnet for routine engineering work; Haiku 4.5 for fast lightweight calls.
All Claude models work in every Kilo-supported surface: VS Code, Cursor, Windsurf, Trae, JetBrains IDEs (IntelliJ, PyCharm, WebStorm, Android Studio, GoLand, RubyMine), and the Kilo CLI / terminal.
Anthropic models on Kilo Code are billed at the underlying API rates with no markup. Claude Opus pricing starts at $5.00 per million input tokens and $25.00 per million output. Claude Sonnet is roughly $3 / $15. Claude Haiku is $1 / $5. Cache reads are heavily discounted across the family.
No. Anthropic does not publish Claude weights. All Claude usage requires an API key, which Kilo Code provides through its hosted gateway or via your own Anthropic, AWS Bedrock, or Google Vertex key.
Opus is the largest, most capable, and most expensive — best for ambiguous long-horizon engineering. Sonnet is the everyday workhorse: fast enough for interactive coding, accurate enough for non-trivial refactors. Haiku is the cheapest and fastest, useful for short fixups and high-volume sub-agent work.
All Claude models work in every Kilo-supported surface: VS Code, Cursor, Windsurf, Trae, JetBrains IDEs (IntelliJ, PyCharm, WebStorm, Android Studio, GoLand, RubyMine), and the Kilo CLI / terminal.
Install Kilo Code and get instant access to Anthropic: Claude Opus 4.6 and 5 other Anthropic models, plus 500+ frontier and open-source options. Free to start, no credit card required.