Standard Compute
← All models

Claude Sonnet 4.6

Balanced

The default daily driver for agents — most of Opus's quality at a fraction of the price.

Anthropic
Maker
91/100
Overall
50
Value score
$6.60
Blended /1M
1M
Context
Proprietary
Weights
Pricing: $3.00 in · $15 out / 1M tokens · synced from OpenRouter · updated 2026-08-02

Scorecard

Output Quality9.1/10 · 78% community
Agentic Ability9.2/10 · 78% community
Speed8.0/10 · 73% community
Value for $8.0/10 · 72% community
Reliability9.4/10 · 79% community

Claude Sonnet 4.6 is the workhorse of the Claude line and one of the most popular models for everyday agent use. It captures most of Opus's coding ability at roughly half the input price and noticeably faster, which is why many agents default to it and escalate to Opus only when needed. The 1M-token context matches the flagship.

Strengths
  • Near-flagship quality at a much lower price
  • Fast enough for interactive agent loops
  • 1M-token context
Trade-offs
  • Still steps behind Opus on the very hardest tasks
  • Pricier than open-weight models of similar quality

Agents that run Sonnet 4.6 well

The everyday agent default — strong quality without the flagship price.

Best model for Claude CodeBest model for ClineBest model for AiderBest model for CursorBest model for OpenCodeBest model for OpenClaw

Not sure which Claude to run? Best Claude Model in 2026: Opus vs Sonnet vs Haiku →

Claude Sonnet 4.6 FAQ

Is Claude Sonnet 4.6 good for AI agents?
The everyday agent default — strong quality without the flagship price. On our editorial scoring it rates 9.2/10 for agentic ability and 9.1/10 for output quality. Near-flagship quality at a much lower price.
How much does Claude Sonnet 4.6 cost?
Via OpenRouter, Claude Sonnet 4.6 is priced at $3.00 in · $15 out / 1M tokens — a blended rate of about $6.60 per 1M tokens for typical input-heavy agent use.
What is Claude Sonnet 4.6's context window?
Claude Sonnet 4.6 has a 1M-token context window — large enough to hold sizeable codebases or document sets in a single run. Anthropic is the maker.
Can I self-host Claude Sonnet 4.6?
No — Claude Sonnet 4.6 is a proprietary, hosted-only model from Anthropic. You access it through an API (e.g. OpenRouter) rather than running the weights yourself.
What are the downsides of Claude Sonnet 4.6?
The main trade-offs: still steps behind opus on the very hardest tasks; pricier than open-weight models of similar quality. It's strongest for the everyday agent default — strong quality without the flagship price.

Sonnet 4.6 compared

Sonnet 4.6 vs TerraSonnet 4.6 vs GPT-5.4Sonnet 4.6 vs Gemini 3.5 FlashSonnet 4.6 vs GPT-5.3-CodexSonnet 4.6 vs Kimi K2.7 CodeSonnet 4.6 vs MiniMax M3Sonnet 4.6 vs Qwen3.7 PlusSonnet 4.6 vs Devstral 2

The model is half the story — the agent is the other half

The model picks the moves; the agent runs the loop, the tools, and the guardrails. Once you've chosen a model, see which agent gets the most out of it.

Compare AI agents →

Every model on this page is included with Standard Compute

Standard Compute

Current frontier models Claude Fable 5 · GPT-5.6 Sol

Your agents never stop.
Your bill never grows.

Frontier models when it counts. Efficient models when it doesn’t. No usage limits. One flat bill.

Free trial · no card · plans from $39/mo

Free trial No credit card needed Billing by Stripe4,700+ agent users