Models

Kiro gives you access to frontier and open weight AI models. Each model has different strengths, so you can pick the right one for the job or let Kiro decide for you by selecting Auto.

Quick comparison

Cost is relative to Auto (1.0x baseline). For example, a task that costs 10 credits on Auto would cost 22 credits on Opus, 4 credits on Haiku, or 0.5 credits on Qwen3 Coder Next.

How to switch models

Use the model dropdown in the chat interface, or set your default from the command line. If for some reason a model from the list above does not show up in the drop down, restart your client and that should resolve the issue.

kiro-cli settings chat.defaultModel claude-opus4.6

To save your current model as the default for all future sessions:

> /model set-current-as-default

This stores your preference in ~/.kiro/settings/cli.json. New sessions automatically use this model.

Which model should you use?

Model details

Auto (recommended)

Kiro's model router. Auto combines multiple frontier models with optimization techniques to deliver the best quality-to-cost ratio. It automatically chooses the optimal model for each task and delivers Sonnet 4-class results. Auto uses best-in-class LLM models (Claude Sonnet 4 and similar) and maintains a high quality bar to ensure results compare to or exceed the individual models available to you.

Claude Opus 4.6

Anthropic's most capable model with state-of-the-art coding and agentic performance. Top scores on Terminal-Bench 2.0 and SWE-bench Verified for agentic coding. Stays productive over longer sessions without context drift and handles multi-million-line codebases, planning upfront and adapting as needed. Improved debugging and code review capabilities let it catch its own mistakes, and it thinks more carefully on complex problems, revisiting reasoning before committing. Learn more.

Claude Opus 4.5

Anthropic's most intelligent model, combining maximum capability with practical performance. Significant improvements in reasoning, coding, and problem-solving at a more accessible price point than previous Opus models. Handles tradeoffs and ambiguity well across multiple systems, making it suited for the most sophisticated software development challenges. Learn more.

Claude Sonnet 4.6

A full upgrade from Sonnet 4.5 that approaches Opus 4.6 intelligence while being more token efficient. Excels at iterative development workflows and maintains context across long sessions. Handles both lead agent and subagent roles in multi-model pipelines, making it well-suited for teams using Kiro powers and custom subagents. Learn more.

Claude Sonnet 4.5

Anthropic's best model for complex agents and coding, with the highest intelligence across most tasks. State-of-the-art on SWE-bench Verified with extended autonomous operation for hours with effective tool usage. Improved planning, system design, and security engineering. Learn more.

Claude Sonnet 4.0

Direct access to Anthropic's Claude Sonnet 4.0 for users who prefer consistent model selection. Same model for all interactions with no routing or optimization layers. Full control and complete transparency, with predictable behavior for workflows that depend on specific model characteristics. Learn more.

Claude Haiku 4.5

Anthropic's fastest model with near-frontier performance. Matches Sonnet 4 performance across reasoning and coding at more than twice the speed. Near-frontier intelligence at one-third the cost, and the first Haiku model with extended thinking capabilities. Learn more.

DeepSeek 3.2

Open weight model best suited for agentic workflows and code generation. Handles long tool-calling chains, stateful sessions, and multi-step reasoning well. 0.25x credit multiplier with inference running in US East (N. Virginia). Learn more.

MiniMax 2.1

Open weight model best suited for multilingual programming and UI generation. Delivers strong results across Rust, Go, C++, Kotlin, TypeScript, and others. 0.15x credit multiplier with inference running in US East (N. Virginia) and EU (Frankfurt). Learn more.

Qwen3 Coder Next

Open weight model purpose-built for coding agents with 256K context and strong error recovery. Works especially well for long agentic coding sessions in the CLI. 0.05x credit multiplier, the most cost-effective option available, with inference running in US East (N. Virginia) and EU (Frankfurt). Learn more.

How models behave differently

Not all models work the same way. Understanding these differences helps you pick the right one.

Planning depth: Opus models think longer before acting. They plan multi-step approaches, consider edge cases, and revisit their reasoning. Sonnet and Haiku are more direct: they start working sooner and iterate faster.

Self-correction: Opus 4.6 in particular is better at catching its own mistakes during code review and debugging. If you're seeing bugs in generated code, switching to Opus can help.

Session endurance: For long-running tasks (like working through a spec), Opus models maintain focus better over extended sessions. Haiku and Sonnet are better suited for shorter, focused interactions.

Initiative level: Opus models tend to take more initiative, making broader changes when they see opportunities. Sonnet is more conservative and sticks closer to what you asked for. Choose based on whether you want the model to lead or follow.

Model lifecycle

Models in Kiro go through two stages. Each stage reflects the model's maturity and the level of support you can expect.

Launch dates

Best practices

• Start with Auto for most work. It optimizes both quality and cost automatically.
• Switch to Opus when you hit a wall on a complex problem or need sustained multi-file work.
• Use Haiku for quick iterations, simple fixes, or when you want to conserve credits.

• Monitor your usage in your account settings to understand how model choice affects consumption.
• Factor model cost into your tier: If you primarily use Opus, consider Pro+ or Power for more credits. See plans and billing for details.